© 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. 80672
    Prev
    Next
    INDEX
    Explanations

    exception handling code

    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
        
    -1.73
    ’,
    -1.65
    我們
    -1.65
     
    -1.63
            
    -1.60
           
    -1.59
     their
    -1.57
     
    -1.54
    勐
    -1.52
                
    -1.51
    POSITIVE LOGITS
    什么的
    2.08
    "> 
    1.77
    檍
    1.67
     uſed
    1.64
    
    1.63
     脸
    1.57
    ᡝ
    1.55
    纐
    1.54
     完了
    1.53
     molti
    1.52
    Activations Density 0.001%

    No Known Activations