© 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. 1141
    Prev
    Next
    INDEX
    Explanations

    image references with anchors

    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
                     
    -2.02
                    
    -1.89
             
    -1.87
              
    -1.84
                                  
    -1.74
           
    -1.73
                
    -1.71
    Following
    -1.70
        
    -1.70
                           
    -1.68
    POSITIVE LOGITS
    絎
    1.71
    ㉔
    1.66
    ugges
    1.62
    abı
    1.55
     perfons
    1.52
    ’
    1.51
    揹
    1.51
     studia
    1.50
    neue
    1.50
     nowy
    1.50
    Activations Density 0.002%

    No Known Activations