© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72833
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with subscripts and superscripts

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

    The neuron detects numeric literals containing decimal (floating‐point) values.

    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
     fabia
    -1.65
    珧
    -1.58
    鹩
    -1.52
     spiele
    -1.52
    ⚋
    -1.48
     Fórmula
    -1.47
     jamón
    -1.45
     Muerte
    -1.44
    {\
    -1.41
     antena
    -1.41
    POSITIVE LOGITS
    ↵
    1.81
    遑
    1.80
    分に
    1.63
    '])
    1.52
    '].
    1.52
    )?
    1.50
     aislada
    1.50
     such
    1.50
    しなかった
    1.48
     is
    1.46
    Activations Density 0.013%

    No Known Activations