© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75375
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

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

    The neuron activates on numeric tokens—digits or numbers (often with decimals or as part of math notation).

    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
    🧫
    -2.30
     of
    -1.82
     pēc
    -1.76
     Jerusalén
    -1.71
     also
    -1.70
    ⁝
    -1.70
     órg
    -1.59
     nepiecieš
    -1.59
    López
    -1.58
     īpa
    -1.56
    POSITIVE LOGITS
     then
    2.48
     ก็
    1.77
     فقط
    1.77
    Conclusie
    1.74
     chré
    1.71
    を使って
    1.71
     メニュー
    1.67
    त्तर
    1.57
     Then
    1.55
    Then
    1.53
    Activations Density 0.031%

    No Known Activations