© 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. 10-GEMMASCOPE-RES-131K
    7. 69274
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ganadores
    -1.35
     exigencias
    -1.27
     billetes
    -1.23
     Pastikan
    -1.22
     Organizador
    -1.22
    .-"
    -1.22
    fucker
    -1.20
    örk
    -1.20
    .";
    -1.20
     Gestión
    -1.19
    POSITIVE LOGITS
    0
    1.51
                            
    1.45
                             
    1.38
                    
    1.37
                       
    1.34
    Ten
    1.30
    Of
    1.30
              
    1.30
                
    1.28
                         
    1.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.