© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60426
    Prev
    Next
    INDEX
    Explanations

    vitamins, minerals, and antioxidants

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

    lists of vitamins, minerals, and nutritional components, especially when they appear in comma-separated format.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron specializes in spotting numeric quantity tokens (e.g., numbers, decimals, and measurements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -2.03
     it
    -1.87
     four
    -1.74
     three
    -1.63
     two
    -1.58
     one
    -1.57
     using
    -1.55
     all
    -1.55
    ing
    -1.54
     to
    -1.52
    POSITIVE LOGITS
     غذایی
    1.75
     ไม่มี
    1.66
     diğer
    1.48
    eapples
    1.47
     Lorsque
    1.46
     ไม่
    1.46
     มัน
    1.45
     juzgar
    1.45
    zeichnete
    1.41
     Quando
    1.41
    Activations Density 0.098%

    No Known Activations