© 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. 130661
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on mentions of numerical quantities or enumerations (digits or spelled-out numbers indicating counts, rows, or items).

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

    numbers and quantities

    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
    افع
    -0.93
     mattina
    -0.83
    otts
    -0.82
     достиг
    -0.79
     presence
    -0.76
    っくり
    -0.75
    issants
    -0.75
     presenza
    -0.73
     several
    -0.73
     even
    -0.72
    POSITIVE LOGITS
     ส่วน
    0.93
    poetry
    0.84
    Normals
    0.83
     października
    0.83
     plus
    0.80
     게임
    0.79
     två
    0.78
     วาด
    0.78
     Chemie
    0.78
     policía
    0.77
    Activations Density 0.078%

    No Known Activations