© 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. 179343
    Prev
    Next
    INDEX
    Explanations

    Transfer Tavern

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

    news and industry commentary

    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
    ால்
    0.48
     botanical
    0.47
    ുകാര
    0.47
    労働
    0.47
    ጀ
    0.47
     noemen
    0.46
     woodwork
    0.46
    テル
    0.46
    シューズ
    0.46
     encoders
    0.46
    POSITIVE LOGITS
    ’
    0.69
    ied
    0.68
    iz
    0.52
    ain
    0.52
    ib
    0.49
    iation
    0.48
     Nai
    0.48
     ’
    0.47
    off
    0.46
    (,
    0.46
    Activations Density 0.001%

    No Known Activations