© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1314
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on capitalized named entities—especially personal names, titles, and organization names.

    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
    érant
    0.75
    <unused33>
    0.70
    <unused71>
    0.69
    ।]
    0.69
     جوړونکی
    0.68
    reactant
    0.68
    за
    0.67
    мере
    0.66
    ässer
    0.66
    <unused77>
    0.66
    POSITIVE LOGITS
     Bolsonaro
    0.88
     Netanyahu
    0.87
     Putin
    0.84
     Biden
    0.84
     Duterte
    0.84
      
    0.83
     Brexit
    0.78
     Jokowi
    0.76
     CNN
    0.75
     Pelosi
    0.75
    Activations Density 0.290%

    No Known Activations