© 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. 10-GEMMASCOPE-RES-131K
    7. 98735
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    
    -2.95
    ፨
    -2.75
    
    -2.67
    絝
    -2.56
    oused
    -2.50
    thodoxy
    -2.50
     spearheaded
    -2.47
    vereignty
    -2.44
    
    -2.44
     très
    -2.41
    POSITIVE LOGITS
    There
    3.78
     very
    3.42
     two
    3.27
     one
    3.17
     Since
    3.14
    Those
    3.08
     These
    3.06
     first
    3.05
     relatively
    3.02
     three
    2.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.