© 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. 56751
    Prev
    Next
    INDEX
    Explanations

    group theory and abstract algebra

    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
     plus
    -0.86
    extractor
    -0.84
     TV
    -0.82
     плюс
    -0.80
    lesssim
    -0.80
     komple
    -0.77
     leth
    -0.75
     Models
    -0.74
    arlı
    -0.74
     Magical
    -0.73
    POSITIVE LOGITS
    ^{-
    1.02
     inverse
    0.96
    inverse
    0.93
    )^{-
    0.89
     Conjug
    0.87
     Inverse
    0.85
     Anthropology
    0.84
     Compensation
    0.84
    に参加
    0.79
     Cellar
    0.79
    Activations Density 0.027%

    No Known Activations