© 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. 11526
    Prev
    Next
    INDEX
    Explanations

    dates and names

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

    This neuron primarily detects clause- and sentence-boundary punctuation, especially commas and periods.

    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
     ଚ
    0.63
     केवाईसी
    0.62
     উদ্ধার
    0.61
    ്ര
    0.61
     racc
    0.61
     chcete
    0.57
     paraphernalia
    0.56
     می‌ده
    0.55
    Ყ
    0.55
     खरीदते
    0.55
    POSITIVE LOGITS
     aha
    0.58
     simple
    0.57
    jena
    0.57
    وي
    0.55
    wil
    0.52
    auta
    0.52
    ui
    0.51
     I
    0.51
     accept
    0.51
    AST
    0.51
    Activations Density 0.003%

    No Known Activations