© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30309
    Prev
    Next
    INDEX
    Explanations

    WORKDIR /app

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     egal
    0.47
    怛
    0.46
    OLDS
    0.45
    
    0.43
     ordinary
    0.42
     процен
    0.42
    MORD
    0.42
    
    0.42
    ﺬ
    0.41
    ⟥
    0.41
    POSITIVE LOGITS
     app
    0.62
    app
    0.60
     App
    0.55
     ऐप
    0.53
     앱
    0.52
    App
    0.46
     APP
    0.45
    アプリ
    0.45
     application
    0.44
     Bash
    0.44
    Activations Density 0.002%

    No Known Activations