© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6890
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens and measurements—i.e. it finds numbers, IDs, quantities, or other digit‐based expressions.

    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
    트워크
    0.98
    드가
    0.95
    하고자
    0.95
    ak
    0.91
     וע
    0.87
    岖
    0.86
     Ү
    0.84
     Selatan
    0.84
    ش
    0.84
    ché
    0.82
    POSITIVE LOGITS
     integers
    1.39
     digits
    1.32
    整数
    1.21
     dígitos
    1.20
     чисел
    1.18
     decimals
    1.15
     numerals
    1.14
    数字
    1.12
     fluctuations
    1.11
     числа
    1.08
    Activations Density 1.575%

    No Known Activations