© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13929
    Prev
    Next
    INDEX
    Explanations

    javascript imports

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is triggered by programming‐style tokens—things like quoted module paths (’dart:core’), import syntax (the @, /, and string‐literal quotes), version numbers, dropdown‐component identifiers, etc.—i.e. code-like strings, symbols, and numeric literals.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    the digit '4' appearing in years (particularly in the 1940s range).

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @jyhe0408

    mentions of programming and software development artifacts, especially library/package identifiers, import/module paths, and code-related error or version references.

    oai_token-act-pair · gpt-5
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    JSONObject
    0.58
    咒
    0.56
    HttpPost
    0.56
    Fib
    0.55
     AsyncStorage
    0.55
     Json
    0.55
    ÃO
    0.54
    Png
    0.54
    蟹
    0.54
    二维码
    0.54
    POSITIVE LOGITS
     kuk
    0.55
    ிக்க
    0.53
    kuk
    0.53
     শাস্তি
    0.52
     lattice
    0.51
     بیٹنگ
    0.51
     мед
    0.51
    ルメ
    0.51
    телите
    0.51
    stellt
    0.50
    Activations Density 0.000%

    No Known Activations