© 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. 29981
    Prev
    Next
    INDEX
    Explanations

    small 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
    Negative Logits
    rescence
    -0.85
    ِّ
    -0.83
    @
    -0.77
    衔
    -0.75
    헌
    -0.75
    냥
    -0.73
    大量
    -0.72
    pgm
    -0.71
     collectively
    -0.70
    enetrable
    -0.69
    POSITIVE LOGITS
     groups
    2.75
     grupos
    2.19
    groups
    2.06
    Groups
    1.98
     Groups
    1.96
     breakout
    1.91
    GROUPS
    1.77
     group
    1.77
     groupes
    1.77
     GROUPS
    1.75
    Activations Density 0.027%

    No Known Activations