© 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. 69967
    Prev
    Next
    INDEX
    Explanations

    res, new, bid, one, popular, larger

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

    structure and formality

    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
    USDA
    0.50
    BURY
    0.47
     י
    0.45
    Grande
    0.45
    Zaw
    0.45
    Federal
    0.45
    Virt
    0.44
    Ő
    0.43
    UST
    0.43
    FB
    0.43
    POSITIVE LOGITS
     ballerina
    0.49
    算法
    0.47
    手数
    0.46
     cPix
    0.46
    ブログ
    0.45
    贋
    0.45
     souvent
    0.45
     wrongful
    0.45
     cookieParser
    0.45
     repub
    0.43
    Activations Density 0.001%

    No Known Activations