© 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. 1134
    Prev
    Next
    INDEX
    Explanations

    automakers and car brands

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

    The neuron strongly activates on automotive model references and specifications—especially car model names paired with numeric details like model years or engine figures.

    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
     pedagogical
    0.89
     mnist
    0.81
     細胞
    0.81
     Pedagog
    0.81
     মানবাধিকার
    0.81
     epistem
    0.80
     педаго
    0.79
     педагоги
    0.78
     কমিউনিস্ট
    0.77
     Scaffold
    0.76
    POSITIVE LOGITS
     powertrain
    2.23
     cars
    2.22
     автомобиль
    2.16
    车型
    2.14
     hatchback
    2.13
     автомобиля
    2.09
     Chevrolet
    2.08
     خودرو
    2.03
     차량
    2.03
    รถ
    2.02
    Activations Density 1.279%

    No Known Activations