© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8556
    Prev
    Next
    INDEX
    Explanations

    linking words and follow-ups

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

    The neuron specializes in spotting numeric quantities (especially large or decimal‐formatted numbers).

    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_31_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
    צל
    0.54
    建立了
    0.52
    ling
    0.50
    擔任
    0.50
    ivorous
    0.49
    这个人
    0.49
    Dance
    0.48
    ং
    0.48
    สุดท้าย
    0.47
    วล
    0.47
    POSITIVE LOGITS
    тету
    0.72
    ധാ
    0.61
    ൨
    0.61
     tubules
    0.60
    endas
    0.59
     respeto
    0.57
     abbat
    0.57
     cultura
    0.57
     часу
    0.57
     nondegenerate
    0.56
    Activations Density 0.000%

    No Known Activations