© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127740
    Prev
    Next
    INDEX
    Explanations

    JavaScript object types and properties

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

    The neuron fires on references to ECMAScript’s built-in internal objects, types, and operations (e.g. “Intrinsic,” “Number,” “ToNumber,” “TypeError,” etc.).

    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
     этой
    -1.46
     김
    -1.41
    }`);
    -1.40
     mereka
    -1.40
     parcheggio
    -1.37
     الجلد
    -1.34
    birthdate
    -1.34
    Eksteraj
    -1.30
     femmes
    -1.30
     baloncesto
    -1.26
    POSITIVE LOGITS
     how
    1.41
     by
    1.39
    //
    1.38
     what
    1.36
    if
    1.36
    <em>
    1.35
    кол
    1.35
     the
    1.34
    在她
    1.27
     &
    1.25
    Activations Density 0.139%

    No Known Activations