© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40302
    Prev
    Next
    INDEX
    Explanations

    numbers, units, and punctuation

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

    The neuron flags numeric tokens (numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     only
    -1.21
    tambah
    -1.19
    參考資料
    -1.16
    っけ
    -1.14
    Bagaimana
    -1.13
    瑧
    -1.13
    參見
    -1.13
    Preparazione
    -1.11
    気で
    -1.10
    Доброго
    -1.09
    POSITIVE LOGITS
     alábbi
    1.48
    すっ
    1.33
    ほら
    1.32
    あー
    1.23
    事が
    1.22
     You
    1.22
    MessageTagHelper
    1.17
    ните
    1.16
     ВА
    1.12
     seleccione
    1.12
    Activations Density 0.091%

    No Known Activations