© 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. 152477
    Prev
    Next
    INDEX
    Explanations

    blowing kisses

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

    data processing and organization

    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
    我们要
    0.49
     ആൻ
    0.46
     Tổ
    0.44
    我們要
    0.43
    我们也
    0.42
    ആ
    0.42
     श्रीवास्तव
    0.41
     우리가
    0.41
    naya
    0.40
     ആ
    0.40
    POSITIVE LOGITS
    regexp
    0.52
     electrolytic
    0.50
    ческого
    0.49
    reject
    0.46
    ריק
    0.45
    σιμο
    0.45
     anbef
    0.44
    jetty
    0.44
    ゅう
    0.44
     imitated
    0.44
    Activations Density 0.001%

    No Known Activations