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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14984
    Prev
    Next
    INDEX
    Explanations

    virtual machines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    lesque
    1.49
    escent
    1.46
     preserve
    1.46
     tentatively
    1.39
    껴
    1.38
    틸
    1.38
    鉋
    1.31
    앵
    1.31
    넉
    1.31
     fathom
    1.31
    POSITIVE LOGITS
     намного
    2.69
     অনেক
    2.22
     بشكل
    2.14
     hebat
    2.14
     mafia
    2.13
     فترة
    2.11
     السنوات
    2.10
    冯
    2.09
    劉
    2.08
    扂
    2.08
    Activations Density 0.162%

    No Known Activations