© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14985
    Prev
    Next
    INDEX
    Explanations

    immediate help

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     Sovi
    0.62
     сразу
    0.57
    лага
    0.53
    женных
    0.53
    氈
    0.52
    ложить
    0.52
     кы
    0.51
     flavon
    0.51
     ويا
    0.50
    謐
    0.50
    POSITIVE LOGITS
    िल
    0.56
     কমিশনার
    0.55
    િયો
    0.52
    findOrFail
    0.52
     vínculo
    0.50
    േഖ
    0.49
    िवेशन
    0.49
    handleClick
    0.49
     पदा
    0.49
    LinkId
    0.48
    Activations Density 0.057%

    No Known Activations