© 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. 69001
    Prev
    Next
    INDEX
    Explanations

    mostly qualifying descriptions

    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
     &
    -3.09
     -
    -2.67
     '
    -2.53
     
    -2.39
     of
    -2.20
     I
    -2.20
    ясь
    -2.19
    ↵↵
    -2.19
     &#
    -2.17
     使っ
    -2.14
    POSITIVE LOGITS
    鹮
    2.98
    蕯
    2.73
    zyden
    2.73
    堙
    2.72
     desenli
    2.66
    亊
    2.66
    t
    2.61
    ون
    2.50
    Ꮵ
    2.48
     helg
    2.47
    Activations Density 0.017%

    No Known Activations