© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43381
    Prev
    Next
    INDEX
    Explanations

    forming images

    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
     setor
    -1.47
     such
    -1.46
    ))=
    -1.37
     of
    -1.28
     então
    -1.27
     takich
    -1.21
     then
    -1.20
    向けの
    -1.20
     consci
    -1.19
     hulp
    -1.18
    POSITIVE LOGITS
        
    1.84
                
    1.77
     as
    1.76
             
    1.63
           
    1.63
         
    1.61
          
    1.57
                    
    1.56
                 
    1.53
                   
    1.53
    Activations Density 0.218%

    No Known Activations