© 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. 65752
    Prev
    Next
    INDEX
    Explanations

    pair, organ, economical, crisis

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

    Novak Djokovic and championships

    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
    ام
    0.50
    ף
    0.46
    ית
    0.45
    韬
    0.45
    同學們
    0.44
    ון
    0.44
    我們先
    0.43
     \\
    0.43
    t
    0.43
    中午
    0.42
    POSITIVE LOGITS
    crisis
    0.50
     crises
    0.49
     filosóf
    0.49
    valuer
    0.49
     vêtements
    0.47
    creas
    0.47
    artan
    0.47
     философия
    0.47
    beitet
    0.46
     philosophie
    0.46
    Activations Density 0.000%

    No Known Activations