© 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. 102882
    Prev
    Next
    INDEX
    Explanations

    returned resource or response body

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

    responses, parameters, status codes

    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
    Negative Logits
    leine
    0.41
    bruch
    0.41
    andt
    0.40
    าง
    0.40
     programmatic
    0.40
    anova
    0.38
    lab
    0.38
    change
    0.38
    changed
    0.37
    紋
    0.37
    POSITIVE LOGITS
     sayısı
    0.43
     imaginable
    0.43
     skyscrapers
    0.42
     Fingers
    0.42
     automobiles
    0.41
     возмо
    0.40
     ब्लड
    0.39
     möglichen
    0.39
     spé
    0.38
     milyon
    0.38
    Activations Density 0.000%

    No Known Activations