© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68420
    Prev
    Next
    INDEX
    Explanations

    function

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

    The neuron fires on tokens that denote or describe functions—especially the keyword “function,” arrow “=>” notation, and function type annotations in code and comments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Etimología
    -1.77
     erstes
    -1.73
    呿
    -1.63
    
    -1.63
     rengi
    -1.63
    Kosten
    -1.60
    ilustrasi
    -1.55
    kệ
    -1.54
     キーホルダー
    -1.53
    刳
    -1.53
    POSITIVE LOGITS
    a
    2.16
    -
    1.97
     to
    1.95
    1
    1.86
    x
    1.73
    [
    1.65
    (
    1.61
    ;
    1.59
    ",
    1.59
    1.57
    Activations Density 0.070%
    No Known Activations