© 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. 6129
    Prev
    Next
    INDEX
    Explanations

    parenthesized roman numerals

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

    The neuron fires on the parenthesized list or clause labels (e.g. “(a)”, “(1)”, “(i)”) used to enumerate sections in legal text.

    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
     ću
    0.59
     усіх
    0.57
     extingu
    0.56
     >,
    0.53
     aton
    0.52
     Soder
    0.52
     všet
    0.51
    梢
    0.51
    lerine
    0.50
     contemplation
    0.50
    POSITIVE LOGITS
    LIVE
    0.46
    process
    0.46
    koi
    0.45
     প্রক্র
    0.43
     firstly
    0.43
     pokud
    0.43
    PHYS
    0.43
    liminf
    0.43
    پ
    0.42
     process
    0.42
    Activations Density 0.001%

    No Known Activations