© 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. 72884
    Prev
    Next
    INDEX
    Explanations

    v. Plaintiff-Appellant

    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
    t
    -1.61
     厂家
    -1.59
     手工
    -1.56
     ferrovia
    -1.56
    at
    -1.55
     包装
    -1.55
     货
    -1.51
    😊
    -1.51
     卡片
    -1.49
     照片
    -1.48
    POSITIVE LOGITS
    )।
    1.73
    
    1.61
    樯
    1.48
    ihnachts
    1.43
    籐
    1.42
     که
    1.39
    \}$.
    1.39
    ?”
    1.38
    aneously
    1.37
     if
    1.36
    Activations Density 0.012%

    No Known Activations