© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2470
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on standalone numeric tokens—especially floating‐point numbers—i.e. it detects decimal‐formatted numbers in the text.

    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
                
    0.73
        
    0.68
                            
    0.64
                        
    0.63
                                
    0.63
                    
    0.61
     revanche
    0.61
    <unused2174>
    0.61
     $^{
    0.59
                         
    0.59
    POSITIVE LOGITS
    1.90
    1.53
    1.40
    1.28
    1.22
    1.09
    1.09
    <0xE3>
    1.00
    0.95
    <0xE2>
    0.93
    Activations Density 0.024%

    No Known Activations