© 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. 102898
    Prev
    Next
    INDEX
    Explanations

    lists, titles, article titles

    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
     the
    -2.03
     this
    -1.88
    "
    -1.82
     ,
    -1.80
    );
    -1.75
     some
    -1.74
     your
    -1.71
    ’
    -1.70
     -
    -1.64
     that
    -1.57
    POSITIVE LOGITS
    terscotch
    1.95
    蒾
    1.88
    鈇
    1.84
    葙
    1.79
    OUTUBE
    1.70
    AdvEx
    1.70
    ӊ
    1.62
     histó
    1.62
    觧
    1.59
    ܊
    1.59
    Activations Density 0.013%

    No Known Activations