© 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. 79373
    Prev
    Next
    INDEX
    Explanations

    Redistributions of source code

    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
     vélos
    -1.54
     touristes
    -1.41
     spécialement
    -1.41
     firft
    -1.37
     sillas
    -1.34
     bicicletas
    -1.33
     parachoque
    -1.32
     préparé
    -1.31
     restera
    -1.30
    髏
    -1.30
    POSITIVE LOGITS
         
    2.25
           
    2.22
          
    2.19
        
    2.13
    2.02
     if
    1.90
       
    1.85
     What
    1.83
             
    1.77
     It
    1.65
    Activations Density 0.073%

    No Known Activations