© 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. 27228
    Prev
    Next
    INDEX
    Explanations

    publication and update dates

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

    date labels and timestamps

    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
     चयनित
    0.53
    全長
    0.52
     সেরে
    0.49
    では
    0.48
    ীবনী
    0.47
     नो
    0.47
     சென்னையில்
    0.47
    鉀
    0.47
     সশস্ত্র
    0.46
     તા
    0.46
    POSITIVE LOGITS
     administrator
    0.57
     administrators
    0.54
     listings
    0.49
     manhood
    0.46
     correspondence
    0.46
    correspond
    0.45
     monitors
    0.45
     correlates
    0.44
     upholstery
    0.43
    ก็
    0.42
    Activations Density 0.001%

    No Known Activations