© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72641
    Prev
    Next
    INDEX
    Explanations

    suppliers, shadows, for, follows

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

    API endpoint and execution

    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
    OfWeek
    0.44
    指標
    0.43
    เหล่า
    0.43
     leaderboard
    0.41
    參
    0.41
    γωγ
    0.40
     Daley
    0.40
    だと
    0.40
     funny
    0.39
    Birds
    0.39
    POSITIVE LOGITS
    ∑
    0.49
     insuffisamment
    0.49
     основании
    0.48
    ải
    0.47
    Ū
    0.46
     عمومی
    0.46
    +/-
    0.46
     amply
    0.45
    ờ
    0.45
    ū
    0.45
    Activations Density 0.000%

    No Known Activations