© 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. 22-GEMMASCOPE-RES-131K
    7. 54357
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and terms

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

    The neuron activates on numeric tokens (integers or decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     >=",
    -0.85
    ">&
    -0.81
    **********/
    -0.81
    ((&
    -0.80
     实例
    -0.80
     Sarajevo
    -0.78
    нрави
    -0.77
    ätte
    -0.77
     catena
    -0.77
     спор
    -0.77
    POSITIVE LOGITS
     each
    0.93
     względu
    0.88
     розташо
    0.80
     estekak
    0.80
    žius
    0.79
     Betis
    0.79
    Сі
    0.78
     estric
    0.78
    Ǵ
    0.77
     simple
    0.76
    Activations Density 0.019%

    No Known Activations