© 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. 136575
    Prev
    Next
    INDEX
    Explanations

    planning personal success

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

    antique curios

    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
    ри
    0.54
    le
    0.52
     Socialist
    0.47
    razio
    0.46
    рида
    0.45
    ра
    0.44
    詩
    0.43
    ری
    0.43
    он
    0.43
     Caballero
    0.43
    POSITIVE LOGITS
     উপযোগী
    0.48
     වශ
    0.48
     alcoved
    0.47
     eprintln
    0.47
     मुख्यालय
    0.46
     ঘন্টার
    0.46
     HNO
    0.46
     échanc
    0.45
     HOUR
    0.44
     इन्हे
    0.44
    Activations Density 0.000%

    No Known Activations