© 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. 45537
    Prev
    Next
    INDEX
    Explanations

    sam, bur, dav, QL

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     *
    -4.25
     -
    -4.06
     '
    -4.00
    2
    -3.98
     {
    -3.91
     s
    -3.75
    ing
    -3.67
    a
    -3.66
     ;
    -3.59
     (
    -3.55
    POSITIVE LOGITS
     itſelf
    4.16
    蹋
    3.72
    犼
    3.70
    
    3.63
    銪
    3.52
    硨
    3.50
    禩
    3.44
    
    3.42
    
    3.34
    鋌
    3.31
    Activations Density 0.012%

    No Known Activations