© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7554
    Prev
    Next
    INDEX
    Explanations

    property, env, calculated, import

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

    This neuron fires on unusually rare or low‐frequency tokens—typically uncommon words or proper names.

    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_24_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
    OptionPane
    0.69
    罗斯
    0.69
    它
    0.69
    有问题
    0.68
     gewährle
    0.68
    。
    0.68
    та
    0.65
    যোগ্য
    0.65
    зен
    0.65
    manship
    0.64
    POSITIVE LOGITS
    최
    0.91
     ছয়
    0.74
     setSelected
    0.72
     भक्तों
    0.72
     बहुतेक
    0.72
     Algunos
    0.72
     좋아하는
    0.71
     Ис
    0.70
     гульнявыя
    0.70
    elekt
    0.70
    Activations Density 0.001%

    No Known Activations