© 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. 13819
    Prev
    Next
    INDEX
    Explanations

    medical diagnostic terms

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

    The neuron specifically detects numeric references—section numbers, ordinals, and other standalone numbers—in the 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
    ถุน
    0.79
    あ
    0.76
     Bulletin
    0.71
     squeez
    0.70
     ফকির
    0.69
    waan
    0.68
    シール
    0.68
    이지만
    0.68
    IZA
    0.66
     flound
    0.66
    POSITIVE LOGITS
    ם
    0.83
     carotid
    0.79
    מור
    0.71
     prakty
    0.67
    fps
    0.67
     bioactive
    0.67
     potrebno
    0.66
     مطل
    0.66
     tumour
    0.66
    punkte
    0.66
    Activations Density 0.000%

    No Known Activations