© 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. 1077
    Prev
    Next
    INDEX
    Explanations

    app screen contexts

    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
    になりたい
    -2.03
    読んで
    -1.78
     ของ
    -1.73
     favoris
    -1.73
    一是
    -1.67
     There
    -1.66
     levier
    -1.64
    蹀
    -1.64
     conquista
    -1.63
    ικοί
    -1.62
    POSITIVE LOGITS
    n
    2.47
    an
    2.17
    ll
    2.13
    ri
    2.05
     solches
    2.02
    for
    1.91
     =
    1.88
     mite
    1.84
    (
    1.82
     ganzes
    1.80
    Activations Density 0.006%

    No Known Activations