© 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. 47113
    Prev
    Next
    INDEX
    Explanations

    database relationships and linking tables

    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
     dạng
    -0.84
    𝙁
    -0.79
    Glorious
    -0.79
    που
    -0.77
    Contras
    -0.77
     çev
    -0.77
     nomme
    -0.75
    Batter
    -0.75
    างเกง
    -0.75
    Durée
    -0.75
    POSITIVE LOGITS
     relationship
    2.33
     relation
    1.95
     relación
    1.94
     association
    1.83
     relationships
    1.82
     relations
    1.66
    relationship
    1.61
    relation
    1.54
    关系
    1.53
     linking
    1.50
    Activations Density 0.036%

    No Known Activations