© 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. 85137
    Prev
    Next
    INDEX
    Explanations

    posts, stats, or highlights

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

    Minimal API

    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
     Bezirk
    0.47
    Ethiop
    0.47
    َّة
    0.46
    /*.
    0.43
    )".
    0.42
    Ду
    0.42
     Capitalism
    0.42
     издания
    0.42
    ènement
    0.42
     Ethiop
    0.42
    POSITIVE LOGITS
     batter
    0.50
     spanning
    0.49
    珴
    0.49
     bother
    0.49
     fondos
    0.48
     flooring
    0.47
     coz
    0.47
     spanned
    0.46
     যাবতীয়
    0.46
     wouldn
    0.46
    Activations Density 0.000%

    No Known Activations