© 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. 130169
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on numeric tokens—especially floating-point numbers (decimal measurements or dosages).

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

    numbers and separators

    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
    ÁB
    -1.09
     estrellas
    -0.94
     éter
    -0.94
    kier
    -0.91
    ？」
    -0.90
    Сюжет
    -0.90
    Семья
    -0.88
    rías
    -0.88
     Segundo
    -0.88
    Δια
    -0.87
    POSITIVE LOGITS
    怎么能
    1.06
     jednej
    0.98
    ystems
    0.97
     //
    0.96
     जिसमें
    0.92
     unrecogn
    0.91
     encontra
    0.88
     ഒരു
    0.86
    InInspector
    0.85
    干嘛
    0.84
    Activations Density 0.002%

    No Known Activations