© 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. 35381
    Prev
    Next
    INDEX
    Explanations

    touch bar

    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
    Negative Logits
    ococcal
    0.39
    setHorizontal
    0.39
    貝
    0.38
    ωσε
    0.38
    िफाई
    0.38
     xứ
    0.38
     المب
    0.37
     presc
    0.37
     sourceType
    0.37
    羯
    0.37
    POSITIVE LOGITS
     trunk
    1.45
    trunk
    1.33
     Trunk
    1.32
     trunks
    1.16
     Touch
    1.14
    Touch
    1.03
     tronco
    0.97
     TOUCH
    0.91
    TOUCH
    0.81
     touch
    0.80
    Activations Density 0.002%

    No Known Activations