© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13537
    Prev
    Next
    INDEX
    Explanations

    equity and fairness

    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
        
    -3.23
          
    -3.05
                 
    -2.67
                    
    -2.56
     Thirty
    -2.55
     dando
    -2.52
                                   
    -2.52
     ehemalige
    -2.50
                            
    -2.50
               
    -2.47
    POSITIVE LOGITS
    леми
    2.56
     juga
    2.44
    笄
    2.34
    蛧
    2.30
    昙
    2.30
     prepara
    2.28
    💕
    2.25
    儈
    2.25
    Они
    2.22
    のほうが
    2.22
    Activations Density 0.002%

    No Known Activations