© 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. 9734
    Prev
    Next
    INDEX
    Explanations

    latex math equations and code

    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
     робити
    0.47
     tickers
    0.47
     KPIs
    0.45
    https
    0.44
    लाक
    0.44
    蹉
    0.43
     subpoenas
    0.43
    ریٹر
    0.43
    ຂໍ້ມູນ
    0.42
     rağmen
    0.42
    POSITIVE LOGITS
     生
    0.44
     '
    0.42
    色彩
    0.42
     pigment
    0.42
     ディ
    0.41
     り
    0.41
     を
    0.40
     व
    0.39
    ForegroundColor
    0.39
    >\
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.