© 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. 13-GEMMASCOPE-2-RES-65K
    7. 627
    Prev
    Next
    INDEX
    Explanations

    python function definitions

    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_13_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
    و
    0.86
    Doctrine
    0.74
     субъек
    0.72
     vii
    0.72
     во
    0.71
     проведен
    0.71
    ل
    0.71
    ল
    0.70
     мер
    0.69
     erschienen
    0.67
    POSITIVE LOGITS
    rainment
    1.02
    ottle
    1.00
    affee
    0.97
    arend
    0.96
     campground
    0.95
     Sweeney
    0.95
    weeney
    0.95
    atah
    0.95
    andal
    0.94
     railroad
    0.94
    Activations Density 0.512%

    No Known Activations