© 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. 222218
    Prev
    Next
    INDEX
    Explanations

    window cleaning, trustee education, Frank Underwood, Access Control

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

    hidden magical traditions

    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
     Amtrak
    0.51
     Chevy
    0.50
    tuk
    0.50
     Quebec
    0.49
     ಸಾಮ
    0.49
    ↵
    0.48
     bosque
    0.47
     ofta
    0.47
     Fau
    0.47
     miš
    0.47
    POSITIVE LOGITS
    க
    0.49
    iology
    0.47
    動
    0.47
    ए
    0.45
    roidism
    0.45
    -//
    0.45
     থাকুক
    0.44
    晞
    0.44
    动
    0.43
    endosi
    0.43
    Activations Density 0.001%

    No Known Activations