© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2433
    Prev
    Next
    INDEX
    Explanations

    solve equations for variables

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

    The neuron never fires—it does not activate on any token.

    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_24_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
    िशनर
    0.69
    ，“
    0.67
    ，《
    0.67
    वाधिकार
    0.67
     aventure
    0.67
     persön
    0.66
    präsident
    0.65
    檄
    0.65
     అంశ
    0.64
     વિશે
    0.63
    POSITIVE LOGITS
              
    0.80
          
    0.79
                        
    0.79
                      
    0.77
    an
    0.77
    a
    0.77
                    
    0.77
                
    0.76
     =
    0.76
            
    0.75
    Activations Density 0.004%

    No Known Activations