© 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. 236999
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    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
    ベイ
    0.45
    baud
    0.44
    （
    0.42
    convention
    0.41
    productList
    0.41
     및
    0.40
    лог
    0.40
    index
    0.40
     placées
    0.40
     suspicious
    0.39
    POSITIVE LOGITS
    ၵ
    0.50
     optimize
    0.47
    য়ের
    0.47
     አማ
    0.46
    న్
    0.46
    𝖑
    0.46
     optimized
    0.46
    ాగ
    0.46
     భాగంగా
    0.45
    𝙣
    0.45
    Activations Density 0.000%

    No Known Activations