© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12933
    Prev
    Next
    INDEX
    Explanations

    culture, heritage, ethnicity

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

    This neuron activates on words and phrases related to personal identity and origins—family relationships, ancestry, heritage, nationality, and cultural or ethnic background.

    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
     uređ
    0.76
    监狱
    0.74
     unbearable
    0.73
     専用
    0.71
    ⌓
    0.70
     inutil
    0.70
    ุปกรณ์
    0.68
     düny
    0.67
    mills
    0.67
    يارات
    0.67
    POSITIVE LOGITS
     ancestry
    1.25
     ethnicities
    1.23
     ethnicity
    1.17
     ethnic
    1.09
     Ethnicity
    1.06
    Ethn
    1.02
     ancestors
    1.01
    祖
    1.00
    ethn
    1.00
     nationality
    0.98
    Activations Density 0.087%

    No Known Activations