© 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. 14097
    Prev
    Next
    INDEX
    Explanations

    points and borders

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

    The neuron is primarily activated by numeric expressions, figures, and measurement‐related tokens 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
    Église
    0.79
    婚礼
    0.78
    并在
    0.78
     painstaking
    0.76
     مسیر
    0.76
    नई
    0.73
    盪
    0.73
    ongoing
    0.70
    Од
    0.70
    tennis
    0.70
    POSITIVE LOGITS
    ot
    0.78
     reached
    0.74
    st
    0.73
     siap
    0.73
    w
    0.73
     gate
    0.71
     excepted
    0.71
    wa
    0.70
    वटी
    0.70
    f
    0.70
    Activations Density 1.928%

    No Known Activations