© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104413
    Prev
    Next
    INDEX
    Explanations

    java code and questions

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     damen
    -1.32
     bensin
    -1.25
     menyen
    -1.23
    artik
    -1.23
     retrô
    -1.20
     berken
    -1.19
     its
    -1.18
     Spanyol
    -1.18
     inginkan
    -1.17
     hunde
    -1.16
    POSITIVE LOGITS
    ,
    1.27
       
    1.23
          
    1.14
    </strong>
    1.13
    ua
    1.12
    </em>
    1.09
      
    1.08
         
    1.05
                                
    1.05
                  
    1.05
    Activations Density 0.000%

    No Known Activations