© 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. 11488
    Prev
    Next
    INDEX
    Explanations

    R package and data analysis terms

    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
     Paolo
    0.46
     Sid
    0.43
     Find
    0.42
    ના
    0.41
    [
    0.41
    円
    0.41
     l
    0.41
     Edwin
    0.41
    .
    0.41
     Drag
    0.41
    POSITIVE LOGITS
     між
    0.54
     ಮನೆಯ
    0.53
    slidesPer
    0.52
    keyPressed
    0.48
     giữa
    0.47
    між
    0.46
    нется
    0.46
     ব্রিটেনের
    0.45
    리로
    0.45
    kehr
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.