© 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. 8909
    Prev
    Next
    INDEX
    Explanations

    describing different types of activity

    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
     بشه
    -1.70
     verbinding
    -1.69
    鑁
    -1.66
    ventes
    -1.65
     gesprek
    -1.62
     oplossing
    -1.61
     bedrag
    -1.60
     geschenk
    -1.58
     geheel
    -1.57
     volledig
    -1.56
    POSITIVE LOGITS
         
    2.11
              
    2.06
                               
    2.02
            
    2.00
             
    1.98
                                   
    1.95
        
    1.91
                        
    1.89
                         
    1.85
                     
    1.83
    Activations Density 0.022%

    No Known Activations