© 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. 83689
    Prev
    Next
    INDEX
    Explanations

    ID and values in parentheses

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

    SQL INSERT statements

    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
     advantageous
    0.40
     exportation
    0.40
     frequency
    0.39
     ruffle
    0.39
     {[
    0.39
     coefficient
    0.39
     coefficients
    0.39
     percentage
    0.38
     conditions
    0.38
    িন্দা
    0.38
    POSITIVE LOGITS
     تاریخی
    0.44
    媧
    0.43
     anta
    0.42
    🐗
    0.42
    }}$.
    0.41
    гие
    0.41
     ofer
    0.41
     Valerie
    0.41
     после
    0.41
    歷史
    0.41
    Activations Density 0.000%

    No Known Activations