© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 452
    Prev
    Next
    INDEX
    Explanations

    This neuron lights up on programming‐style punctuation and symbol tokens (like semicolons, braces, comment markers, and other nonletter characters common in code).

    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
    ږئ
    0.39
     hausse
    0.39
     تړ
    0.39
    ړئ
    0.37
     ताब्यात
    0.37
    تدائي
    0.36
     विषया
    0.36
     व्हाउचर
    0.36
    ینګ
    0.36
     بیاکت
    0.36
    POSITIVE LOGITS
        
    0.77
    	
    0.75
    //
    0.72
            
    0.68
    		
    0.68
    /*
    0.66
    #
    0.64
    ////////////////
    0.63
    print
    0.61
          
    0.61
    Activations Density 0.128%

    No Known Activations