© 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. 104940
    Prev
    Next
    INDEX
    Explanations

    web server

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

    symbols and abbreviations

    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
     døde
    0.47
    醋
    0.46
     vilá
    0.46
     मंगल
    0.45
     melewati
    0.44
     vért
    0.44
     hielo
    0.44
     রু
    0.43
    ëm
    0.43
     limón
    0.43
    POSITIVE LOGITS
    기
    0.57
    유
    0.52
    제가
    0.52
    Q
    0.50
    ქ
    0.50
    О
    0.48
    sql
    0.48
    ﺍ
    0.48
    VIEW
    0.47
    @
    0.47
    Activations Density 0.000%

    No Known Activations