© 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. 247674
    Prev
    Next
    INDEX
    Explanations

    season Participating pros

    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
    отя
    0.56
     істори
    0.54
    ној
    0.52
    alista
    0.51
    뀌
    0.50
     estadounid
    0.49
    يسي
    0.48
     долларов
    0.47
    揮
    0.47
    тися
    0.47
    POSITIVE LOGITS
    Portal
    0.46
    Logging
    0.45
    Notes
    0.44
    pr
    0.43
    Part
    0.43
    にと
    0.43
    observation
    0.43
    print
    0.43
    DT
    0.42
    Range
    0.42
    Activations Density 0.001%

    No Known Activations