© 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. 80628
    Prev
    Next
    INDEX
    Explanations

    shot followed by action or object

    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
    on
    -2.98
    th
    -2.94
    {
    -2.91
    of
    -2.75
     mesmer
    -2.67
    after
    -2.59
    as
    -2.53
    轵
    -2.44
    m
    -2.39
    ()
    -2.34
    POSITIVE LOGITS
    '
    3.45
    杁
    2.78
    ꜆
    2.70
     denselben
    2.48
     gewiß
    2.45
     erwor
    2.44
     They
    2.44
    嘮
    2.36
    屙
    2.36
     erreich
    2.33
    Activations Density 0.015%

    No Known Activations