© 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. 104598
    Prev
    Next
    INDEX
    Explanations

    environment, floats, or itemize environments

    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
    …»
    -1.43
    ismo
    -1.37
    \_\_
    -1.36
    wwwww
    -1.34
     serveur
    -1.34
    !»
    -1.33
     odi
    -1.30
     batterie
    -1.30
    ोर्ट
    -1.30
    轲
    -1.29
    POSITIVE LOGITS
     about
    1.63
                     
    1.44
     yaklaşık
    1.40
                        
    1.35
            
    1.31
                       
    1.30
     மற்ற
    1.30
                   
    1.28
               
    1.28
                      
    1.27
    Activations Density 0.048%

    No Known Activations