© 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. 165966
    Prev
    Next
    INDEX
    Explanations

    increased topic or niche

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

    text wrapping with tab-separated values

    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
    髮
    0.48
    鉐
    0.48
     Reconciliation
    0.44
    不敢
    0.44
     pokud
    0.44
    ující
    0.43
     Slave
    0.42
    年には
    0.42
    髪
    0.42
    的には
    0.41
    POSITIVE LOGITS
     automate
    0.47
     unspo
    0.46
    лесо
    0.46
     overcrow
    0.46
     impulse
    0.45
     sweetheart
    0.44
    yaw
    0.44
    LIBRARY
    0.43
    Q
    0.43
    emptyDict
    0.43
    Activations Density 0.001%

    No Known Activations