© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67823
    Prev
    Next
    INDEX
    Explanations

    javascript click events

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

    This neuron detects JavaScript event names (like “click,” “change,” “load”) used in event-binding calls.

    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
     amazingly
    -1.73
     REALLY
    -1.72
     deliciously
    -1.69
     dando
    -1.68
     ridiculously
    -1.66
     wonderfully
    -1.66
     focuses
    -1.64
    ⎔
    -1.64
     exhilarating
    -1.64
     decidedly
    -1.63
    POSITIVE LOGITS
     and
    2.69
     with
    2.31
     while
    2.16
     or
    2.11
    ,
    1.87
     through
    1.84
    While
    1.71
     substantially
    1.71
     regardless
    1.68
     amidst
    1.66
    Activations Density 0.005%

    No Known Activations