© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15655
    Prev
    Next
    INDEX
    Explanations

    SQL INSERT statements

    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
    GroupBy
    0.60
     stanovnika
    0.57
    给
    0.57
    SqlServer
    0.55
     給
    0.54
     ভারতকে
    0.54
    nvarchar
    0.54
    GraphQl
    0.54
    वय
    0.54
    GROUP
    0.53
    POSITIVE LOGITS
     VALUES
    0.63
     (...)
    0.63
     Werte
    0.61
     ("
    0.61
     values
    0.60
     (`
    0.60
     Values
    0.60
     ()
    0.59
     (_,
    0.55
     (…)
    0.55
    Activations Density 0.000%

    No Known Activations