© 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. 83672
    Prev
    Next
    INDEX
    Explanations

    .on() event handlers

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

    The neuron strongly activates on occurrences of the “on” token when it’s used to register event listeners (e.g. `.on(…)`).

    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
     we
    -1.75
    ’
    -1.73
    accéder
    -1.60
     their
    -1.54
     câteva
    -1.54
     cercando
    -1.51
    lo
    -1.49
     Their
    -1.45
     hinted
    -1.44
    ội
    -1.41
    POSITIVE LOGITS
    錞
    1.79
    ⍽
    1.63
    Dalam
    1.58
    </sup>
    1.55
    Players
    1.53
    рована
    1.52
    unuz
    1.49
    🅶
    1.48
    Czytaj
    1.47
     borracha
    1.45
    Activations Density 0.003%

    No Known Activations