© 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. 100117
    Prev
    Next
    INDEX
    Explanations

    prevent default actionsglycemia and preterm birth

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

    JavaScript and web programming functions related to preventing default behaviors.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects calls to the JavaScript event.preventDefault (and related preventDefault) method.

    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
    y
    -2.92
    in
    -2.64
    at
    -2.45
    also
    -2.36
     beruht
    -2.33
     Also
    -2.14
     
    -2.09
    都有
    -2.06
    也会
    -2.05
     ändert
    -2.03
    POSITIVE LOGITS
    聍
    3.03
    ᕱ
    2.97
    慙
    2.61
    olymers
    2.59
    脔
    2.55
    ౬
    2.48
    鹟
    2.47
    ჱ
    2.45
    馘
    2.45
    狴
    2.39
    Activations Density 0.003%

    No Known Activations