© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3787
    Prev
    Next
    INDEX
    Explanations

    administrator privileges

    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_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ķ
    0.56
    在全球
    0.52
     Kamane
    0.49
     û
    0.47
    ubishi
    0.47
    era
    0.46
     kö
    0.46
    )}}{
    0.46
    柺
    0.46
     Members
    0.45
    POSITIVE LOGITS
     axioms
    0.54
     reactivation
    0.54
    이트
    0.51
     interstices
    0.51
     shipbuilding
    0.50
     Khalil
    0.49
     subgraph
    0.48
    ド
    0.47
     variational
    0.46
    기
    0.46
    Activations Density 0.000%

    No Known Activations