© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13674
    Prev
    Next
    INDEX
    Explanations

    David followed by surname

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

    The neuron strongly activates on occurrences of the proper name “David.”

    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
     współprac
    0.64
     ESP
    0.61
    헨
    0.61
    千里
    0.60
     synov
    0.58
     DUT
    0.57
     devised
    0.56
     IBS
    0.56
     Exped
    0.55
     UNIVERS
    0.55
    POSITIVE LOGITS
    heiser
    0.62
    lng
    0.58
    owitz
    0.57
    esting
    0.57
    ઔ
    0.57
    ItemList
    0.56
     بالم
    0.55
    embalikan
    0.55
    unable
    0.54
     సినిమాలో
    0.54
    Activations Density 0.040%

    No Known Activations