© 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. 148580
    Prev
    Next
    INDEX
    Explanations

    following fields

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

    pieces, leaves, media, representation, writings

    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
     Judd
    0.55
     JUD
    0.55
     Джу
    0.52
     राउत
    0.50
     אך
    0.49
     такому
    0.49
     INVEST
    0.49
     눈
    0.48
     अध्याय
    0.48
     투자
    0.47
    POSITIVE LOGITS
    0
    0.51
    ز
    0.47
    عر
    0.47
    زين
    0.46
    لت
    0.45
    obenzene
    0.44
    φος
    0.43
    he
    0.43
    放置
    0.42
    en
    0.42
    Activations Density 0.001%

    No Known Activations