© 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. 4071
    Prev
    Next
    INDEX
    Explanations

    country

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

    www . com links

    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
    RatingDiff
    0.29
    ݢ
    0.28
     ennemis
    0.28
     traitor
    0.27
     misog
    0.26
     humiliation
    0.26
     উপসং
    0.26
     culpa
    0.25
     Wahrheit
    0.25
     ถ้า
    0.25
    POSITIVE LOGITS
    DC
    0.27
    Media
    0.26
    MAX
    0.25
    MISS
    0.25
    CA
    0.25
    <0xE2>
    0.24
    Director
    0.24
    Flex
    0.24
     said
    0.24
    K
    0.23
    Activations Density 0.213%

    No Known Activations