© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14489
    Prev
    Next
    INDEX
    Explanations

    character, horizontal, interface, address

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

    The neuron is looking for decimal numbers (floating‐point numerals, as in journal volume or page numbers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    h
    0.83
    im
    0.79
     заданной
    0.78
    th
    0.77
    y
    0.77
    las
    0.75
    lation
    0.74
    laboratory
    0.74
    yx
    0.73
    ्वेस्ट
    0.73
    POSITIVE LOGITS
     unión
    0.89
    0.88
    ﺎ
    0.80
    ο
    0.73
     declaró
    0.72
    ীর
    0.71
     religión
    0.71
    韓国
    0.70
     userId
    0.70
     convirtió
    0.70
    Activations Density 0.000%

    No Known Activations