© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15384
    Prev
    Next
    INDEX
    Explanations

    son of

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

    The neuron activates on kinship terms indicating parent–child relationships (e.g. “son” or “daughter”).

    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
     sprem
    0.74
    ي
    0.73
     newborns
    0.70
     kobi
    0.68
     sním
    0.68
     henne
    0.67
    يون
    0.66
    yog
    0.65
     bab
    0.65
     hende
    0.64
    POSITIVE LOGITS
        
    1.02
          
    0.95
    OfThe
    0.89
            
    0.81
                
    0.79
         
    0.73
                            
    0.73
    、
    0.73
    Of
    0.73
                  
    0.72
    Activations Density 0.018%

    No Known Activations