© 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. 1083
    Prev
    Next
    INDEX
    Explanations

    play tic tac toe with

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

    This neuron detects uncommon, content-rich tokens—especially proper nouns, technical terms, and other specific or rare words.

    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
     Tage
    0.54
     Inoltre
    0.50
     infine
    0.50
     সেক্ষেত্রে
    0.50
     seguir
    0.49
     messo
    0.49
     oth
    0.49
     Haag
    0.49
     bian
    0.48
     TBA
    0.48
    POSITIVE LOGITS
     例文帳に追加
    0.95
    例文帳に追加
    0.88
    <0xC2>
    0.83
    様専用
    0.83
     букмекерлар
    0.73
     阅读全文
    0.72
    …。
    0.70
     کاسینو
    0.69
    ？
    0.69
    ﹐
    0.68
    Activations Density 17.951%

    No Known Activations