© 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. 22-GEMMASCOPE-RES-131K
    7. 129810
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively fires on standalone numeric tokens (digits or numbers) inside mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mathematical notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ַּ
    -1.83
    ERICK
    -1.68
     Rússia
    -1.52
    𐍆
    -1.48
    setBold
    -1.46
     camada
    -1.44
     ActionResult
    -1.41
    ֶּ
    -1.40
    ִּ
    -1.37
    haviours
    -1.34
    POSITIVE LOGITS
    '
    1.41
     arcilla
    1.33
     hermosas
    1.24
     
    1.21
     hermosos
    1.21
     immense
    1.21
     мальчика
    1.19
     aleación
    1.17
     четырех
    1.17
     here
    1.17
    Activations Density 0.004%

    No Known Activations