© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15871
    Prev
    Next
    INDEX
    Explanations

    ko-, Kon-, Ko-, Kel-, Kom-, Kor- prefixes

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

    The neuron strongly activates on tokens containing the substring “Ko,” especially in proper names that begin with “Ko.”

    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
    Containing
    0.62
    ideon
    0.61
    紋
    0.60
    Coefficient
    0.59
    imètre
    0.57
     coefficient
    0.55
    رمز
    0.55
     Coefficient
    0.55
     কর্মী
    0.54
    画布
    0.54
    POSITIVE LOGITS
     Oct
    0.56
    ्यो
    0.53
     Jul
    0.52
     नवम्बर
    0.52
     июля
    0.52
    Ỗ
    0.50
     мая
    0.49
     ikut
    0.49
     macar
    0.49
    Oct
    0.49
    Activations Density 0.090%

    No Known Activations