© 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. 5172
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

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

    The neuron is triggered by code-oriented tokens—especially file‐extension indicators (like “.sh”, “.js”, “.php”) and programming identifiers/constants.

    oai_token-act-pair · o4-mini
    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
     '%'
    0.58
    ‘’
    0.57
     返回
    0.57
    वारा
    0.55
     savaş
    0.55
    Called
    0.55
     создание
    0.54
    壓
    0.54
    देखिए
    0.54
     llamó
    0.54
    POSITIVE LOGITS
     Lle
    0.59
    stechnik
    0.59
     Amt
    0.57
    ANTES
    0.57
     Rok
    0.55
     Contractor
    0.55
     contractor
    0.55
    inale
    0.55
     đốc
    0.52
     VD
    0.52
    Activations Density 0.000%

    No Known Activations