© 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. 7726
    Prev
    Next
    INDEX
    Explanations

    .js or .ts files

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

    The neuron detects JavaScript module or component names (i.e. the identifiable “.js” filename segments) embedded in file‐path URLs.

    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
     equals
    0.70
     so
    0.68
    _
    0.67
     =
    0.66
    Base
    0.63
     varchar
    0.61
    ViewHolder
    0.61
     MVC
    0.59
     implements
    0.59
    DTO
    0.59
    POSITIVE LOGITS
    ranu
    0.65
     त्यांनी
    0.63
    īn
    0.62
    thorn
    0.61
     ترى
    0.61
    .";
    0.61
    िलं
    0.60
    étaient
    0.59
    altet
    0.59
    antung
    0.59
    Activations Density 0.001%

    No Known Activations