© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3294
    Prev
    Next
    INDEX
    Explanations

    numerical properties and counts

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

    list of numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
     कब्जे
    0.43
     تعداد
    0.42
    Cuánt
    0.41
    坫
    0.40
    窩
    0.39
    多久
    0.39
     pushedAt
    0.39
    哄
    0.38
    总量
    0.38
    anniksi
    0.38
    POSITIVE LOGITS
     numbers
    3.50
    numbers
    3.31
     Numbers
    3.25
    Numbers
    3.09
     números
    3.03
    數字
    2.91
    数字
    2.86
     чисел
    2.86
     числа
    2.80
     Zahlen
    2.72
    Activations Density 0.102%

    No Known Activations