© 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. 24625
    Prev
    Next
    INDEX
    Explanations

    Go language, Google, modules, build

    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
    西班牙
    0.42
    
    0.41
     باسک
    0.41
     Испании
    0.40
    нта
    0.40
     farlo
    0.40
    🪵
    0.40
    ਫ
    0.39
     allowNull
    0.39
    ᱷ
    0.39
    POSITIVE LOGITS
    Google
    0.53
     Go
    0.51
     Google
    0.50
    Go
    0.50
    cross
    0.48
    Official
    0.48
    google
    0.47
     google
    0.47
    GOOGLE
    0.45
     modest
    0.45
    Activations Density 0.006%

    No Known Activations