© 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. 13058
    Prev
    Next
    INDEX
    Explanations

    JUnit 5 DisplayName and extensions

    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
    Negative Logits
    বাবুর
    0.41
    鎮
    0.39
    InfoWindow
    0.38
     মুজিবকে
    0.38
    الوجی
    0.38
    ostatistics
    0.38
     মুজিবের
    0.38
     irreducible
    0.38
    *{-
    0.38
    EROS
    0.37
    POSITIVE LOGITS
    DisplayName
    0.63
    extension
    0.51
    displayName
    0.49
     disabled
    0.49
    Disabled
    0.48
     displayName
    0.48
     extension
    0.44
     Disabled
    0.43
    🟢
    0.43
    jupiter
    0.40
    Activations Density 0.001%

    No Known Activations