© 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. 106470
    Prev
    Next
    INDEX
    Explanations

    group theory and Lie groups

    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
    Not in Any Lists

    No Comments

    Negative Logits
     generator
    -1.02
    generator
    -0.91
     generators
    -0.88
     Generator
    -0.87
    Generator
    -0.87
     Generators
    -0.84
    generators
    -0.78
    olic
    -0.76
    Sprint
    -0.74
    ebp
    -0.73
    POSITIVE LOGITS
     group
    1.04
     autom
    1.00
     groups
    0.96
    GL
    0.93
     GL
    0.86
     Aut
    0.82
    autom
    0.82
    Vou
    0.81
     گروه
    0.80
    GroupName
    0.76
    Activations Density 0.051%

    No Known Activations