© 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. 216077
    Prev
    Next
    INDEX
    Explanations

    professional services

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

    page length of documents

    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
    Chocolate
    0.57
    Lamb
    0.54
    Kart
    0.53
    chocolate
    0.53
    巧克力
    0.53
    ঙ্গার
    0.52
    ナー
    0.50
    隻
    0.49
    とにかく
    0.49
    ઑ
    0.49
    POSITIVE LOGITS
     Erfol
    0.56
     İs
    0.55
     raison
    0.50
     Expo
    0.49
     Headlines
    0.49
     erreur
    0.48
     ဖြစ်
    0.47
     �
    0.47
     ιστο
    0.47
     glorie
    0.46
    Activations Density 0.000%

    No Known Activations