© 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. 26942
    Prev
    Next
    INDEX
    Explanations

    switch variations and related devices

    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
    蛹
    0.39
    変化
    0.39
     ลง
    0.39
    моби
    0.38
    徥
    0.37
    дент
    0.37
    ائز
    0.37
    acom
    0.37
    屽
    0.37
    특별시
    0.37
    POSITIVE LOGITS
     switched
    0.86
     switch
    0.75
     Switch
    0.73
     Switching
    0.73
     switching
    0.73
     स्विच
    0.72
     switches
    0.68
     Switches
    0.67
    switch
    0.66
    Switch
    0.66
    Activations Density 0.002%

    No Known Activations