© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11499
    Prev
    Next
    INDEX
    Explanations

    new Promise, Axios, Date, ArrayBuffer

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

    The neuron fires strongly on documentation-style type declarations and related markers—e.g. tokens like “:”, “string”, “number”, “boolean”, “node:”, numeric values, and similar labels that show up when defining or listing API/data field types.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     |
    0.80
     ||
    0.62
     interface
    0.62
     +
    0.60
     Many
    0.60
     @
    0.57
     &
    0.56
     Someone
    0.54
     Multi
    0.53
    Strong
    0.53
    POSITIVE LOGITS
    itzer
    0.73
     desconoc
    0.66
     {[
    0.64
    विण्यासाठी
    0.64
    ènes
    0.63
    FURNIZOR
    0.63
     टाक्या
    0.63
    ipid
    0.63
    ｛
    0.63
    incor
    0.62
    Activations Density 0.002%

    No Known Activations