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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128783
    Prev
    Next
    INDEX
    Explanations

    code punctuation and keywords

    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
    Not in Any Lists

    No Comments

    Negative Logits
     either
    -1.45
    ㆆ
    -1.45
     auffi
    -1.43
     drau
    -1.41
     Fieber
    -1.37
     avanza
    -1.36
    ſelf
    -1.36
     joyous
    -1.33
     vixion
    -1.33
     WORLD
    -1.32
    POSITIVE LOGITS
    錚
    1.86
     with
    1.76
    =}
    1.61
        
    1.55
           
    1.52
    特别是
    1.52
            
    1.49
                  
    1.48
          
    1.43
              
    1.41
    Activations Density 0.007%

    No Known Activations