© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3013
    Prev
    Next
    INDEX
    Explanations

    end of sentence or list item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⟋
    0.59
    ′
    0.49
     socalled
    0.48
    ″
    0.48
     ′
    0.47
     উপজে
    0.46
     —
    0.44
    ड़ियों
    0.42
    springframework
    0.42
    谀
    0.41
    POSITIVE LOGITS
      
    3.06
       
    2.38
        
    2.05
          
    2.05
         
    1.95
            
    1.91
              
    1.90
           
    1.84
               
    1.73
                  
    1.72
    Activations Density 0.200%

    No Known Activations