© 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. 72815
    Prev
    Next
    INDEX
    Explanations

    financial terms and measurements

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

    storage expansion

    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
     ஒப்பு
    0.51
     மாதம்
    0.50
    傃
    0.50
     ﺍ
    0.49
     এডিনবার্গ
    0.47
     caffè
    0.47
     कम्पनी
    0.47
     Trivia
    0.46
     ಮಕ್ಕಳ
    0.46
    ishima
    0.46
    POSITIVE LOGITS
    Way
    0.53
     processus
    0.50
    Long
    0.50
    H
    0.49
    Level
    0.48
    Joy
    0.47
    Broad
    0.46
    Su
    0.46
     reed
    0.46
    Xi
    0.45
    Activations Density 0.000%

    No Known Activations