© 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. 58510
    Prev
    Next
    INDEX
    Explanations

    jquery event binding

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

    The neuron fires on jQuery event‐binding calls (e.g. “.on(…)”, “live(…)”).

    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
     we
    -1.74
    lo
    -1.38
     never
    -1.32
     rigue
    -1.30
    nements
    -1.27
     haven
    -1.24
     deur
    -1.24
    隷
    -1.23
     cannot
    -1.23
    tilled
    -1.22
    POSITIVE LOGITS
    سوال
    1.63
    錞
    1.53
    Mujer
    1.52
    Definitely
    1.51
    Actually
    1.48
    Hopefully
    1.48
    Karakteristik
    1.48
    ',
    1.46
    Зно
    1.46
    Bukan
    1.45
    Activations Density 0.010%

    No Known Activations