© 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. 21493
    Prev
    Next
    INDEX
    Explanations

    Batman, Birdman, gothic

    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
    StarGo
    0.42
    HIDE
    0.40
     ಓ
    0.40
     घटनाओं
    0.38
    WithMessage
    0.37
    Sach
    0.37
    conder
    0.37
     озера
    0.36
     plot
    0.36
     ===============
    0.36
    POSITIVE LOGITS
     Burton
    0.52
     goth
    0.43
    आईपी
    0.42
     Gothic
    0.41
     Beetle
    0.41
     gothic
    0.40
    ビッグ
    0.40
    ียบ
    0.39
    ிறு
    0.38
    )}{\
    0.36
    Activations Density 0.001%

    No Known Activations