© 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. 72332
    Prev
    Next
    INDEX
    Explanations

    affiliated withsnowman for saleimpending doomkari says he

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

    foreign numbers and programming concepts

    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
    a
    0.54
    -
    0.52
    ‐
    0.47
    ה
    0.46
    ’
    0.46
     Princess
    0.44
    ści
    0.44
    >
    0.44
    i
    0.43
    s
    0.43
    POSITIVE LOGITS
     gemüt
    0.49
     již
    0.49
     ház
    0.49
    ഷ്ട്ര
    0.49
     Akademie
    0.48
     بيت
    0.47
     ज़कात
    0.46
     قريب
    0.46
     بالفعل
    0.46
     fêtes
    0.46
    Activations Density 0.001%

    No Known Activations