© 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. 40-GEMMASCOPE-2-RES-262K
    7. 169629
    Prev
    Next
    INDEX
    Explanations

    researchers and

    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/layer_40_width_262k_l0_medium
    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
    လှ
    0.37
     ښ
    0.37
    বল
    0.37
     écran
    0.36
     župan
    0.35
     Izv
    0.35
    營養
    0.35
    oč
    0.34
     coerce
    0.34
     приста
    0.34
    POSITIVE LOGITS
    比较
    0.40
    thoughts
    0.40
    겨
    0.39
    极大
    0.38
     thoughts
    0.38
     생각을
    0.36
     Dickinson
    0.36
    York
    0.36
     finisher
    0.36
     Resident
    0.36
    Activations Density 0.000%

    No Known Activations