© 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. 22631
    Prev
    Next
    INDEX
    Explanations

    keywords and labels

    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
    スポンサーリンク
    -1.70
     広場
    -1.61
     adesivo
    -1.61
     ones
    -1.52
    そうですね
    -1.48
    ఝ
    -1.44
     multiuso
    -1.43
     zodiaco
    -1.43
     those
    -1.41
     nhưng
    -1.41
    POSITIVE LOGITS
           
    1.66
                     
    1.60
             
    1.60
                    
    1.57
     You
    1.51
        
    1.48
         
    1.44
                            
    1.43
              
    1.41
                 
    1.41
    Activations Density 0.002%

    No Known Activations