© 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. 6531
    Prev
    Next
    INDEX
    Explanations

    Gro, Buck, Gross, 8

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

    The neuron reliably fires on capitalized name fragments (proper nouns).

    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
    甜
    0.58
    most
    0.57
    oderma
    0.55
    ufact
    0.54
    糖
    0.53
    ogluc
    0.53
    candy
    0.52
    尤
    0.51
     হাতে
    0.51
    ooq
    0.50
    POSITIVE LOGITS
    >−</
    0.74
    >-</
    0.73
    >=</
    0.72
    )}-\
    0.60
    >;</
    0.60
     مشتمل
    0.59
     aliran
    0.59
    >→</
    0.57
     optimally
    0.57
    গঠনিক
    0.57
    Activations Density 0.087%

    No Known Activations