© 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. 45322
    Prev
    Next
    INDEX
    Explanations

    little secret or walk of fame

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

    arc, Weight, interleaving

    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
    不堪
    0.49
    有可能
    0.48
    没有什么
    0.48
    斌
    0.48
    却没有
    0.46
    錆
    0.45
     hesitation
    0.43
    नेश
    0.43
    liers
    0.42
     filthy
    0.42
    POSITIVE LOGITS
    element
    0.52
     À
    0.51
     tradicionales
    0.51
    Israel
    0.50
    スクリーン
    0.50
     フリー
    0.49
    ał
    0.48
    À
    0.48
    XT
    0.47
    device
    0.46
    Activations Density 0.000%

    No Known Activations