© 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. 947
    Prev
    Next
    INDEX
    Explanations

    type/kind of

    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
     if
    -2.09
    　『
    -2.02
    Ꭳ
    -1.99
    ついに
    -1.86
    今朝
    -1.81
    梅雨
    -1.76
    桖
    -1.75
    茨城
    -1.73
    青森
    -1.73
    iniques
    -1.73
    POSITIVE LOGITS
     概念
    1.87
     tuss
    1.84
    all
    1.79
     magnific
    1.75
     verschied
    1.74
     frequentemente
    1.72
    re
    1.69
     COULD
    1.67
     imprescin
    1.64
    '
    1.63
    Activations Density 0.004%

    No Known Activations