© 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. 129639
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric tokens (numbers, measurements, ratios) in the text.

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

    numerical ratios

    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
     motivadoras
    -1.09
    личи
    -1.05
    函館
    -0.93
     jonka
    -0.93
    个月
    -0.90
    ̞
    -0.87
    があります
    -0.87
    DllImport
    -0.85
    嗤
    -0.85
    ってみました
    -0.85
    POSITIVE LOGITS
     ratio
    1.83
     ratios
    1.52
    ratio
    1.48
    ratios
    1.45
     Ratio
    1.41
     Ratios
    1.34
    Ratio
    1.30
    比例
    1.27
     RATIO
    1.23
    RATIO
    1.23
    Activations Density 0.026%

    No Known Activations