© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9868
    Prev
    Next
    INDEX
    Explanations

    column headers or parameters

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on code tokens that are entirely uppercase (e.g. single-letter flags or all-caps words) in shell/build scripts.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     XNUMX
    0.58
     ಅವರನ್ನು
    0.55
    是没有
    0.52
    縝
    0.51
     errand
    0.50
     presence
    0.49
    ಿಯನ್ನು
    0.49
    <a>
    0.48
    ပါ။
    0.48
    NUMX
    0.48
    POSITIVE LOGITS
         
    3.42
          
    3.41
             
    3.41
           
    3.39
               
    3.34
              
    3.28
                 
    3.20
                   
    3.09
                     
    3.09
                  
    3.08
    Activations Density 0.266%

    No Known Activations