© 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. 73967
    Prev
    Next
    INDEX
    Explanations

    history and numbers

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

    buzzed

    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
     විශ්
    0.59
     şekilde
    0.58
    ăpadă
    0.56
    ğe
    0.54
     револю
    0.54
    laublich
    0.54
     dată
    0.53
    镟
    0.53
    álov
    0.52
     lorsque
    0.51
    POSITIVE LOGITS
    0
    0.53
     History
    0.47
     Gujarati
    0.46
     four
    0.45
     Organizing
    0.45
     announcing
    0.44
     seven
    0.44
     encrypted
    0.44
     eight
    0.43
     common
    0.43
    Activations Density 0.001%

    No Known Activations