© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47102
    Prev
    Next
    INDEX
    Explanations

    subversion or averted actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    궁
    -0.83
     (
    -0.77
    ids
    -0.72
    undle
    -0.70
    udesta
    -0.69
     Deter
    -0.68
    ydı
    -0.68
    uo
    -0.67
     but
    -0.66
    num
    -0.66
    POSITIVE LOGITS
     subversion
    1.85
     subver
    1.63
     Lamps
    1.61
    verted
    1.54
     sub
    1.52
     averted
    1.49
     Zig
    1.38
     Sub
    1.38
     subtype
    1.38
     invoked
    1.29
    Activations Density 0.015%

    No Known Activations