© 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. 56687
    Prev
    Next
    INDEX
    Explanations

    traditional dance and folk performances

    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
    cía
    -0.84
     parfü
    -0.81
     listy
    -0.78
     undervis
    -0.78
     kritik
    -0.78
     etik
    -0.77
     Lehmann
    -0.75
    რო
    -0.75
     klinik
    -0.74
    nii
    -0.74
    POSITIVE LOGITS
     dance
    2.14
     dances
    1.79
     folk
    1.61
     performances
    1.61
     Dance
    1.42
     performed
    1.42
     dancing
    1.41
     dancers
    1.41
     performing
    1.41
     perform
    1.40
    Activations Density 0.016%

    No Known Activations