© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7610
    Prev
    Next
    INDEX
    Explanations

    Bluetooth, flight, Axon, TLC, ISO

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

    The neuron fires strongly on tokens that are numeric or alphanumeric specification codes (e.g. model numbers, ratings, IP‐style codes) typically found in product spec sheets.

    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
    ترض
    0.68
    ကျွန်
    0.65
    踵
    0.64
     Garth
    0.64
    คาเดมี
    0.63
    Dollars
    0.63
    ریض
    0.62
    axter
    0.62
     COMMUNICATIONS
    0.62
    衿
    0.61
    POSITIVE LOGITS
     Xiaomi
    1.11
     Xiao
    1.04
     Yuan
    0.98
     Shenzhen
    0.97
     Qing
    0.97
     xia
    0.96
     Nanjing
    0.93
     Alibaba
    0.92
     Sino
    0.92
     yuan
    0.91
    Activations Density 0.504%

    No Known Activations