© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5959
    Prev
    Next
    INDEX
    Explanations

    the process, the web

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

    The neuron is a high‐activation detector for the definite article “the.”

    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
    這個
    0.75
    这个
    0.73
    other
    0.66
    )';
    0.64
    了这个
    0.64
     weiteren
    0.62
    したのは
    0.61
    的這個
    0.60
    其余
    0.60
    偌
    0.60
    POSITIVE LOGITS
     cytoskeleton
    0.71
     sexes
    0.66
     Ausland
    0.65
     workforce
    0.65
     alá
    0.64
     cuticle
    0.63
     arts
    0.63
     hogar
    0.63
     menstrual
    0.62
     circadian
    0.61
    Activations Density 0.368%

    No Known Activations