© 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. 10744
    Prev
    Next
    INDEX
    Explanations

    research directions

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

    The neuron is detecting numeric citation metadata (volume, issue, page, and year numbers) in reference listings.

    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
    ванных
    0.95
    󰡔
    0.87
    <unused76>
    0.86
    ккей
    0.86
     लोकतांत्रिक
    0.85
     никаких
    0.83
    таны
    0.82
    дии
    0.81
    рке
    0.81
     соревнования
    0.81
    POSITIVE LOGITS
     t
    1.27
    0
    1.00
     l
    0.95
    n
    0.94
    ت
    0.91
    l
    0.88
     m
    0.86
     br
    0.82
     قد
    0.82
    '
    0.82
    Activations Density 0.001%

    No Known Activations