© 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. 16097
    Prev
    Next
    INDEX
    Explanations

    ist of, hout Report, Slim Patch

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

    names followed by context

    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
    ↵↵
    0.27
     but
    0.27
     luminosity
    0.27
     to
    0.26
    ↵
    0.26
     परंतु
    0.26
     parameters
    0.26
     emanating
    0.26
     परन्तु
    0.25
    ↵↵↵
    0.25
    POSITIVE LOGITS
    主义
    0.27
     കേന്ദ്ര
    0.26
    йн
    0.25
     হলাম
    0.24
    зал
    0.24
    ઓએ
    0.24
     مزاج
    0.24
    嶅
    0.24
     ছিলাম
    0.24
     Downtown
    0.23
    Activations Density 0.000%

    No Known Activations