© 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. 11730
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation symbols

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

    The neuron spikes on the first substantive content word at the start of a new paragraph or section.

    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
    કુ
    0.75
    تج
    0.73
    薢
    0.72
     nə
    0.71
     الفلسطيني
    0.70
     НЕ
    0.70
     રૂપિયા
    0.69
    눈
    0.69
    渗
    0.68
    ме
    0.67
    POSITIVE LOGITS
     birefring
    0.73
     Syst
    0.72
    ional
    0.70
    0
    0.69
     Lange
    0.69
     Koon
    0.69
     account
    0.67
    ाइए
    0.67
     conceivable
    0.66
     interactive
    0.66
    Activations Density 0.000%

    No Known Activations