© 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. 11020
    Prev
    Next
    INDEX
    Explanations

    address, locations, or codes

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

    The neuron fires strongly on title‐ or heading‐style text—e.g. words in major section headings, labels, or other prominent, capitalized document metadata.

    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
    racting
    0.71
    циями
    0.66
    ǹ
    0.66
    riture
    0.64
     बाती
    0.64
    resultlist
    0.64
    productos
    0.64
    hardening
    0.64
    modulo
    0.63
    timevals
    0.62
    POSITIVE LOGITS
    0.71
     g
    0.70
     {
    0.70
     '
    0.68
     (
    0.66
     -
    0.66
     forgive
    0.64
     orthopedic
    0.63
     "
    0.63
     YMCA
    0.62
    Activations Density 0.006%

    No Known Activations