© 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. 25426
    Prev
    Next
    INDEX
    Explanations

    asking questions about customs

    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
    )
    0.55
     state
    0.54
     U
    0.51
    S
    0.50
    ↵
    0.49
    ↵↵
    0.49
     the
    0.48
     po
    0.48
    U
    0.47
    0.47
    POSITIVE LOGITS
     ['(?
    0.55
    entingan
    0.55
    ungkinkan
    0.55
     bakın
    0.54
     pendekatan
    0.54
    TransactionLog
    0.53
    archiwizowane
    0.52
     movingRect
    0.52
     testaceis
    0.52
    <unused28>
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.