© 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. 57970
    Prev
    Next
    INDEX
    Explanations

    javascript build tools

    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
     where
    -1.32
     aikana
    -1.29
    之时
    -1.23
    之际
    -1.20
     lesquels
    -1.20
     dificil
    -1.17
    voyez
    -1.17
     tacón
    -1.16
     vistazo
    -1.13
    mą
    -1.13
    POSITIVE LOGITS
     to
    1.61
     the
    1.37
                 
    1.24
      
    1.23
                                  
    1.23
             
    1.23
                          
    1.16
     nes
    1.16
     костю
    1.15
    odeficiency
    1.15
    Activations Density 0.059%

    No Known Activations