© 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. 34-GEMMASCOPE-RES-131K
    7. 109595
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    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_34/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
    Liet
    -1.04
    türk
    -1.04
    LikeLike
    -1.00
    menuhi
    -0.99
    obras
    -0.98
     capitulo
    -0.97
     europé
    -0.94
     komment
    -0.94
    entrepreneur
    -0.94
     enää
    -0.93
    POSITIVE LOGITS
               
    1.61
              
    1.60
                       
    1.59
                          
    1.59
                      
    1.57
     |
    1.55
         
    1.55
                     
    1.54
             
    1.53
                                   
    1.51
    Activations Density 0.148%

    No Known Activations