© 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. 13689
    Prev
    Next
    INDEX
    Explanations

    code context delimiters

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

    The neuron fires on tokens that are parts of URLs or file‐system paths—e.g. domain names (org, uk) or directory elements in paths (Windows, Start, etc.).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Interfaces
    0.66
     Dere
    0.61
     Quartet
    0.59
     $("
    0.58
     ------------
    0.58
     Protocol
    0.57
     Toolkit
    0.57
     dispose
    0.57
     Circulation
    0.56
     --------------
    0.55
    POSITIVE LOGITS
    ppling
    0.63
    тным
    0.62
    MONG
    0.61
    planilla
    0.61
     nurturing
    0.60
     presença
    0.59
    蹼
    0.59
    updateConfirm
    0.58
    jobSize
    0.58
    儒
    0.58
    Activations Density 0.000%

    No Known Activations