© 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. 5378
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0.70
    :
    0.63
    -
    0.63
    /
    0.62
    <strong>
    0.59
    g
    0.58
     R
    0.57
    <h3>
    0.57
     Roy
    0.55
    [
    0.54
    POSITIVE LOGITS
     மக்கள
    0.63
     ರೀತಿಯ
    0.63
     размеров
    0.61
    aży
    0.60
     izinsuku
    0.60
     eleições
    0.60
     사이즈
    0.59
     yazı
    0.59
     ພວກເຮົາ
    0.57
     గొప్ప
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.