© 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. 90611
    Prev
    Next
    INDEX
    Explanations

    Gaussian beam, mixture, process, curvature

    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
     That
    -2.98
    ’
    -2.48
    鄚
    -2.36
     However
    -2.31
     unſ
    -2.22
    却又
    -2.16
     ที่
    -2.09
     ہے
    -2.05
     juſt
    -2.05
    這
    -2.02
    POSITIVE LOGITS
     intend
    1.90
     has
    1.88
     unwittingly
    1.85
     και
    1.84
    ไง
    1.84
    鈊
    1.81
    眼下
    1.79
    肜
    1.77
     samego
    1.76
     intelligently
    1.75
    Activations Density 0.003%

    No Known Activations