© 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. 12391
    Prev
    Next
    INDEX
    Explanations

    self-exploration and components

    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
    Agriculture
    0.49
     الزرا
    0.44
    Trou
    0.42
    Pride
    0.42
    諗
    0.42
    ياه
    0.42
    Пи
    0.41
    ordat
    0.41
    บัญ
    0.41
     supremacist
    0.41
    POSITIVE LOGITS
    镙
    0.47
     লাল
    0.47
     strapping
    0.47
     கோயில
    0.46
     країн
    0.46
     Manu
    0.45
     atletas
    0.45
    ೆಯಲ್ಲಿ
    0.44
     然后
    0.44
     Tau
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.