© 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. 205301
    Prev
    Next
    INDEX
    Explanations

    qualitycommentary

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

    bulls are colorblind

    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
    ହି
    0.53
    主席
    0.50
    capi
    0.48
     DNIs
    0.47
     bersama
    0.47
     महापौर
    0.46
     lineColorSpace
    0.45
    visit
    0.44
    ﺪ
    0.44
    めた
    0.44
    POSITIVE LOGITS
     hind
    0.47
    踌
    0.46
    alous
    0.45
     neglect
    0.45
     empt
    0.44
     incurable
    0.43
     ஆ
    0.42
     Reli
    0.42
     trembling
    0.42
     rudimentary
    0.42
    Activations Density 0.003%

    No Known Activations