© 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. 73843
    Prev
    Next
    INDEX
    Explanations

    linking css files

    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
      
    -2.16
            
    -1.89
         
    -1.82
    }$
    -1.79
       
    -1.77
          
    -1.73
    no
    -1.71
                    
    -1.70
     {
    -1.70
             
    -1.67
    POSITIVE LOGITS
    ِي
    1.65
    ㉕
    1.57
    浹
    1.57
     sabes
    1.56
    بله
    1.56
    緜
    1.54
     crianças
    1.54
     ſy
    1.53
     enceinte
    1.52
     sekä
    1.52
    Activations Density 0.007%

    No Known Activations