© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 54591
    Prev
    Next
    INDEX
    Explanations

    display fonts, local ties

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

    content warnings and specific conditions

    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
     منتقل
    0.41
     certificate
    0.40
    Converter
    0.40
     अपनाने
    0.40
    oad
    0.39
    zele
    0.39
    %
    0.39
     வாச
    0.39
    ากาศ
    0.39
     normally
    0.38
    POSITIVE LOGITS
     ⏮
    0.55
    retching
    0.55
    उथ
    0.48
    लिड
    0.47
    ব
    0.47
    дали
    0.47
    র
    0.47
    ब
    0.47
    ล
    0.47
    ហ៊
    0.46
    Activations Density 0.000%

    No Known Activations