© 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. 237211
    Prev
    Next
    INDEX
    Explanations

    open-house days

    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
    selValue
    0.50
    sie
    0.49
    いつも
    0.48
    🏰
    0.48
    стан
    0.48
    避け
    0.48
    жат
    0.47
    ід
    0.47
    ErrorBoundary
    0.47
    стой
    0.46
    POSITIVE LOGITS
    en
    0.53
     r
    0.46
     ring
    0.46
     ganger
    0.46
     dinn
    0.45
    in
    0.44
     Y
    0.44
     h
    0.44
     rupani
    0.44
     Director
    0.43
    Activations Density 0.000%

    No Known Activations