© 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. 34-GEMMASCOPE-RES-131K
    7. 102911
    Prev
    Next
    INDEX
    Explanations

    order and sequence

    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_34/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
    笄
    -0.73
    ongi
    -0.72
    ährend
    -0.71
     tâche
    -0.70
    toHaveBeen
    -0.69
     tecla
    -0.69
    yalar
    -0.68
    øre
    -0.68
    enegger
    -0.67
    IMPORTED
    -0.67
    POSITIVE LOGITS
     order
    6.28
    顺序
    4.69
    order
    4.63
    Order
    4.31
     sequence
    4.19
     ORDER
    4.09
     ordem
    3.95
     Order
    3.94
     Reihenfolge
    3.89
     ordering
    3.75
    Activations Density 0.263%

    No Known Activations