© 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. 163050
    Prev
    Next
    INDEX
    Explanations

    subscription fee

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

    FAQs, tantrums, books, hue, scales

    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
    perate
    0.50
    rational
    0.48
    醣
    0.47
    art
    0.46
    violent
    0.46
    relation
    0.46
    markets
    0.45
    arter
    0.44
    late
    0.43
     المقرر
    0.42
    POSITIVE LOGITS
    ベリー
    0.52
    б
    0.50
    दादा
    0.47
    گ
    0.46
    бы
    0.46
     mulig
    0.46
    ставить
    0.44
    ยายน
    0.44
     găsit
    0.44
    りは
    0.44
    Activations Density 0.000%

    No Known Activations