© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12044
    Prev
    Next
    INDEX
    Explanations

    Client, n, and mathematical notation

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

    The neuron primarily detects numeric expressions (quantities, measurements, and other numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ان
    0.95
    ます
    0.82
    andu
    0.79
    Yang
    0.78
    लू
    0.77
    évaluation
    0.77
    양
    0.75
    एन
    0.74
    滪
    0.74
    φαλ
    0.73
    POSITIVE LOGITS
     gốc
    0.79
     bắt
    0.79
     verschill
    0.79
    ,'
    0.77
     тот
    0.75
     darkMode
    0.73
     Kongo
    0.73
    ,’
    0.73
     regelmäßig
    0.73
     עצ
    0.71
    Activations Density 0.002%

    No Known Activations