© 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. 38591
    Prev
    Next
    INDEX
    Explanations

    App declaration or usage

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

    This neuron detects file‐name tokens with extensions (e.g. “App.css” or “App.js”) in code import or require paths.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ໊
    -1.70
    dann
    -1.66
    蟥
    -1.65
    蛲
    -1.57
    纐
    -1.55
     다른
    -1.53
    
    -1.49
    氿
    -1.49
    artamento
    -1.45
     désign
    -1.45
    POSITIVE LOGITS
    .
    2.59
    !
    1.85
    Not
    1.71
    There
    1.63
    Two
    1.60
    If
    1.60
    Do
    1.56
    :
    1.54
    Just
    1.54
    Like
    1.54
    Activations Density 0.003%

    No Known Activations