© 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. 65085
    Prev
    Next
    INDEX
    Explanations

    Origin Games

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

    reconstruct implementing old

    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
    ng
    0.56
    -
    0.55
     불
    0.52
    es
    0.50
     on
    0.49
    ich
    0.49
    č
    0.49
     ナ
    0.48
    matic
    0.47
    ative
    0.47
    POSITIVE LOGITS
     menghad
    0.49
     ändern
    0.49
    ில்லிய
    0.48
    苋
    0.47
    也就是说
    0.46
     җиңү
    0.45
     handwritten
    0.44
     décrire
    0.44
    عى
    0.44
    错误
    0.43
    Activations Density 0.000%

    No Known Activations