© 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. 159
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

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

    The neuron strongly activates on Chinese personal name tokens.

    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
    يت
    0.30
    ى
    0.29
    rta
    0.27
    inį
    0.26
    ｛
    0.25
    not
    0.25
    remember
    0.25
    ką
    0.25
    inės
    0.25
    ricult
    0.25
    POSITIVE LOGITS
     Fakult
    0.31
     Yu
    0.27
    Yu
    0.27
     Lu
    0.27
     Emily
    0.27
     OSU
    0.27
     Eugenia
    0.27
    Ю
    0.27
    วั
    0.27
     nghiên
    0.26
    Activations Density 0.000%

    No Known Activations