© 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. 5191
    Prev
    Next
    INDEX
    Explanations

    code blocks and parentheses

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

    The neuron strongly activates on numeric tokens—especially large or decimal numbers—typically appearing in parentheses.

    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
     from
    0.74
    ()
    0.71
     for
    0.70
     at
    0.70
     Enrique
    0.69
     Иванович
    0.68
    త్స
    0.68
    ه
    0.68
    ب
    0.66
    (
    0.65
    POSITIVE LOGITS
     पॉलिटी
    0.77
    iller
    0.73
    ounge
    0.70
    paper
    0.70
    <unused375>
    0.70
    Volume
    0.68
    owneri
    0.67
    <unused663>
    0.66
    <unused1158>
    0.66
    <unused628>
    0.64
    Activations Density 0.001%

    No Known Activations