© 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. 150611
    Prev
    Next
    INDEX
    Explanations

    game, replacement, chance, population

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

    sharing actionable insights

    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
    肉
    0.48
    ्यास
    0.46
    啇
    0.45
    当天
    0.44
     klinik
    0.44
    ผ้า
    0.41
    㞱
    0.40
     rued
    0.40
     spind
    0.39
    핸
    0.39
    POSITIVE LOGITS
    orice
    0.50
     και
    0.49
     Strategic
    0.49
     Player
    0.48
     П
    0.48
     Π
    0.48
    J
    0.48
     ভালোবাস
    0.47
    Player
    0.47
    ແລະ
    0.47
    Activations Density 0.000%

    No Known Activations