© 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. 10-GEMMASCOPE-RES-131K
    7. 48401
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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_10/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
    いくら
    -1.80
    K
    -1.73
    u
    -1.70
     สาม
    -1.68
    y
    -1.66
    こども
    -1.62
     เมื่อ
    -1.55
    [
    -1.52
    めんな
    -1.52
    这点
    -1.52
    POSITIVE LOGITS
     about
    1.86
    nipeg
    1.80
     onsdag
    1.68
     in
    1.67
    厶
    1.66
     længere
    1.63
     omkring
    1.62
    blouse
    1.60
    ᒍ
    1.59
    hoodie
    1.58
    Activations Density 0.072%

    No Known Activations