© 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. 1888
    Prev
    Next
    INDEX
    Explanations

    breed-specific considerations

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

    The neuron activates strongly on key content words in product or catalog item titles—i.e. the main nouns and descriptors you’d see in e-commerce listings.

    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
    ↵↵
    0.97
    ↵
    0.84
          
    0.84
               
    0.83
       
    0.79
           
    0.79
     socalled
    0.78
         
    0.78
                 
    0.77
      
    0.75
    POSITIVE LOGITS
     administração
    0.76
     systèmes
    0.69
     ntawm
    0.68
     desempenho
    0.68
     mondiale
    0.68
     opções
    0.67
     modèles
    0.66
     européenne
    0.66
    <unused2127>
    0.65
     proteção
    0.64
    Activations Density 0.409%

    No Known Activations