© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7382
    Prev
    Next
    INDEX
    Explanations

    areas and categories

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

    The neuron fires strongly on words naming domains or specialties (e.g. “area,” “field,” “industry,” “areas”), so it’s detecting mentions of topical or professional/academic fields.

    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
    р
    0.71
    क
    0.70
     p
    0.66
    p
    0.66
    たと
    0.64
     f
    0.64
    IUS
    0.62
    <0x94>
    0.61
     एक
    0.60
     一个
    0.60
    POSITIVE LOGITS
     ciências
    1.46
     ciencias
    1.36
     медици
    1.30
     deportes
    1.20
     scienze
    1.19
     lĩnh
    1.17
     biomed
    1.16
     علوم
    1.16
     gastronomy
    1.16
     astronomy
    1.16
    Activations Density 1.406%

    No Known Activations