© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 145783
    Prev
    Next
    INDEX
    Explanations

    winter and winning

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

    Win and Winter

    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
     REND
    0.51
    摡
    0.50
    بعد
    0.49
     HUNT
    0.49
    barung
    0.48
    ک
    0.48
     Wake
    0.47
    بور
    0.47
     refrained
    0.47
    ”
    0.47
    POSITIVE LOGITS
    WIN
    0.67
    win
    0.66
    Win
    0.62
     Win
    0.59
     win
    0.58
    胜
    0.52
    윈
    0.51
     विजेता
    0.50
    winter
    0.49
     vinto
    0.49
    Activations Density 0.037%

    No Known Activations