© 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. 8250
    Prev
    Next
    INDEX
    Explanations

    past participles followed by prepositions

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

    The neuron strongly activates on numeric sequences—especially floating‐point or decimal numbers such as those used for volume, issue, and page identifiers in citations.

    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
    Numeral
    0.78
    GEBURTS
    0.76
     antiguos
    0.74
     पर्या
    0.71
    ४
    0.71
     instancias
    0.70
     Vogue
    0.70
     인천
    0.70
     procédés
    0.70
     enseign
    0.69
    POSITIVE LOGITS
    соеди
    0.77
    yl
    0.75
    ú
    0.73
    ку
    0.69
     purely
    0.69
    бы
    0.68
    рым
    0.68
    হইতে
    0.68
    зову
    0.67
    ту
    0.67
    Activations Density 0.002%

    No Known Activations