© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 616
    Prev
    Next
    INDEX
    Explanations

    This neuron fires strongly on technical/code‐style tokens—especially numeric values, units (like “pcs”), boolean literals (e.g. “true”), and similar code or data elements.

    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
    gypte
    0.86
    ेंद्रीय
    0.84
    ामान्य
    0.82
    geoning
    0.82
     अल्को
    0.81
    ॕ
    0.79
    𒐪
    0.79
    romagn
    0.77
     कपकेक
    0.77
    ímav
    0.76
    POSITIVE LOGITS
    ↵
    1.26
    1.16
            
    1.15
                
    1.14
    <0x0D>
    1.14
    1.11
    1.09
                        
    1.07
                    
    1.06
        
    1.05
    Activations Density 0.004%

    No Known Activations