© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3346
    Prev
    Next
    INDEX
    Explanations

    This neuron detects version-control diff/patch markers (lines beginning with “+”, “–”, “>”, etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ceased
    0.62
     Nghi
    0.60
     ګټ
    0.59
     weder
    0.57
    ってみ
    0.56
     وګ
    0.56
     Dutt
    0.55
     역
    0.55
     国内
    0.55
     '.</
    0.55
    POSITIVE LOGITS
                    
    2.14
                   
    1.91
                  
    1.88
    1.77
                     
    1.76
                      
    1.71
                 
    1.55
                        
    1.54
                
    1.47
                       
    1.41
    Activations Density 0.016%

    No Known Activations