© 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. 137464
    Prev
    Next
    INDEX
    Explanations

    node data field

    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
    杆
    0.38
     uncover
    0.38
     keys
    0.37
     sociali
    0.37
     csal
    0.37
     المتوسط
    0.36
    Underwater
    0.36
     loc
    0.35
     investigative
    0.35
     loyalty
    0.35
    POSITIVE LOGITS
     choked
    0.41
    ábban
    0.39
    啭
    0.38
     incongru
    0.38
    ándo
    0.37
     Simón
    0.37
     "-
    0.37
     muffler
    0.37
    ekar
    0.37
    NuGetPackage
    0.37
    Activations Density 0.004%

    No Known Activations