© 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. 12416
    Prev
    Next
    INDEX
    Explanations

    events and games

    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
    去
    -1.74
        
    -1.66
     during
    -1.43
                            
    -1.41
     作業
    -1.41
                        
    -1.38
     to
    -1.38
                      
    -1.34
                    
    -1.30
                
    -1.29
    POSITIVE LOGITS
    ｵ
    1.45
     розпові
    1.40
     reflejo
    1.38
    
    1.38
    Setelah
    1.37
     devront
    1.37
    お知らせ
    1.35
     raconte
    1.35
    Недостатки
    1.33
    充滿
    1.33
    Activations Density 0.145%

    No Known Activations