© 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. 6736
    Prev
    Next
    INDEX
    Explanations

    Asian surnames and given names

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

    This neuron detects mentions of personal names (proper names of people).

    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
     увеличение
    0.60
    rschein
    0.60
     казни
    0.59
    猊
    0.59
     मेहता
    0.59
     талант
    0.59
    idescent
    0.58
    ема
    0.57
    Wright
    0.57
    ِمض
    0.57
    POSITIVE LOGITS
     Zhi
    0.71
     Jun
    0.71
     Yong
    0.67
    晓
    0.65
     Guang
    0.64
    氏は
    0.64
     Joon
    0.64
     Jian
    0.62
     Yann
    0.61
     Jie
    0.61
    Activations Density 0.101%

    No Known Activations