© 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. 6728
    Prev
    Next
    INDEX
    Explanations

    division or combination

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

    The neuron fires most strongly on capitalized person or artist names (e.g. “Milind,” “Kamal Raja,” “Mr Jatt”) as they appear in bylines or credit lines.

    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
     ядер
    0.70
     ядра
    0.70
     بأ
    0.64
     ярко
    0.59
     لأ
    0.59
     الأطفال
    0.59
    靖
    0.59
     王
    0.58
     بالأ
    0.58
    炸
    0.57
    POSITIVE LOGITS
     Constantinople
    0.79
     Contoh
    0.71
     conseguido
    0.69
     curcumin
    0.68
     consiguió
    0.66
    cknowled
    0.66
     condolences
    0.65
     còn
    0.63
     kondisi
    0.63
     condiment
    0.63
    Activations Density 1.393%

    No Known Activations