© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103431
    Prev
    Next
    INDEX
    Explanations

    personal names with suffixes

    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
     revel
    -2.19
     extranjeros
    -2.13
     respective
    -2.11
    es
    -2.06
    很多的
    -2.05
    麁
    -2.03
     ''
    -1.94
    无比
    -1.91
    ཿ
    -1.90
     $-$
    -1.89
    POSITIVE LOGITS
    ↵
    3.67
    ’
    2.41
     lampa
    1.95
     “(
    1.91
     rokok
    1.88
    婓
    1.88
    但
    1.86
     们
    1.85
     signifikan
    1.85
     vinil
    1.83
    Activations Density 0.015%

    No Known Activations