© 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. 47576
    Prev
    Next
    INDEX
    Explanations

    games and websites

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

    mathematical or literal connections

    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
     suo
    0.44
     господар
    0.43
     なお
    0.41
     चौधरी
    0.41
     مدر
    0.41
     usos
    0.39
    稼
    0.39
    酝
    0.39
    gono
    0.39
    티브
    0.39
    POSITIVE LOGITS
    /,
    0.45
     ஏற்று
    0.42
    ListArr
    0.42
     দিনে
    0.42
     插
    0.41
     '',
    0.41
     మరియు
    0.41
     verschillende
    0.40
     walnut
    0.40
     coarse
    0.40
    Activations Density 0.000%

    No Known Activations