© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12573
    Prev
    Next
    INDEX
    Explanations

    JavaScript class and prototype definitions

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

    The neuron is detecting references to JavaScript files (“.js” filenames).

    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
    鴳
    0.64
     unteren
    0.63
    रेडी
    0.63
    鵃
    0.62
     hypergeometric
    0.59
    дия
    0.57
    曛
    0.57
    劝
    0.56
    谶
    0.56
    agamanam
    0.55
    POSITIVE LOGITS
     means
    0.62
     spad
    0.59
    importDefault
    0.58
     nep
    0.56
    means
    0.55
     app
    0.54
     piac
    0.54
    読
    0.54
     gr
    0.53
    phal
    0.52
    Activations Density 0.000%

    No Known Activations