© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206031
    Prev
    Next
    INDEX
    Explanations

    county jurisdiction

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

    movement, spent, close, box, understand

    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
     mengisi
    0.54
     mengembangkan
    0.51
     ぐらい
    0.50
     ಹೊ
    0.50
     terrazzo
    0.49
     Himalayas
    0.49
    ?..
    0.49
    訕
    0.48
    utiérrez
    0.47
     ಕ್ಯಾ
    0.47
    POSITIVE LOGITS
    Rotation
    0.54
    i
    0.52
    API
    0.50
     Rotation
    0.50
    rotation
    0.49
    한
    0.49
    Altern
    0.49
     rotation
    0.48
    Flutter
    0.48
    DOM
    0.47
    Activations Density 0.000%

    No Known Activations