© 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. 9320
    Prev
    Next
    INDEX
    Explanations

    Team Foundation Server

    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
    ⵈ
    -2.23
    勦
    -2.03
    给我们
    -2.03
    !’
    -1.98
     夜景
    -1.97
    驁
    -1.94
    says
    -1.88
    …’
    -1.88
    鱘
    -1.88
     ihe
    -1.84
    POSITIVE LOGITS
     of
    2.69
     '
    2.03
    青岛
    1.89
     就是
    1.80
    ｢
    1.77
     Researchers
    1.74
    厦门
    1.69
     Incredible
    1.64
    GGLE
    1.64
    龊
    1.63
    Activations Density 0.004%

    No Known Activations