© 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. 15540
    Prev
    Next
    INDEX
    Explanations

    JavaScript contexts

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

    This neuron activates on the literal token “JavaScript.”

    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
     dekoratif
    -2.63
    ⑉
    -2.53
    樒
    -2.44
    也有
    -2.41
     WHEN
    -2.31
     refugi
    -2.31
    似た
    -2.28
     afir
    -2.25
     kalori
    -2.25
    亖
    -2.23
    POSITIVE LOGITS
    In
    3.23
    .
    3.02
     戰
    2.56
    as
    2.53
    した
    2.52
    畠
    2.50
    酲
    2.39
     esclusivamente
    2.36
    and
    2.34
    Ꭳ
    2.27
    Activations Density 0.019%

    No Known Activations