© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17196
    Prev
    Next
    INDEX
    Explanations

    guides, the clock, Bacteria, in the, takes place

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

    asking for clarification and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     gente
    0.47
    ǃ
    0.47
    orrag
    0.46
    人人
    0.45
    星球
    0.45
    奮
    0.44
    朋友圈
    0.43
    勇敢
    0.42
     LGBTQ
    0.42
    ʘ
    0.41
    POSITIVE LOGITS
     worksheet
    0.48
     adequacy
    0.46
     innymi
    0.46
    蜘
    0.45
    extended
    0.45
    লিখ
    0.44
     summary
    0.44
     parentheses
    0.44
    ERTS
    0.44
     ওয়ার
    0.43
    Activations Density 0.000%

    No Known Activations