© 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. 65319
    Prev
    Next
    INDEX
    Explanations

    Good Enough, Pathfinder OP, answer article

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

    K-factor, Golden Ratio

    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
    匏
    0.57
    噗
    0.52
     kèo
    0.51
    wna
    0.51
     السابع
    0.49
    ジット
    0.48
    𝚓
    0.47
    Violation
    0.47
    鞠
    0.47
     موږ
    0.47
    POSITIVE LOGITS
     sich
    0.54
    laden
    0.50
     regenerate
    0.49
     die
    0.48
     kommer
    0.47
     beste
    0.46
     PM
    0.46
    IR
    0.46
     regener
    0.44
    INION
    0.44
    Activations Density 0.000%

    No Known Activations