© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67316
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    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
     in
    -1.51
     would
    -1.38
    這些
    -1.32
    だわ
    -1.32
    がございます
    -1.26
    だよね
    -1.23
    riendo
    -1.21
     could
    -1.21
    していない
    -1.21
     of
    -1.20
    POSITIVE LOGITS
     любы
    1.36
     ergänzt
    1.28
     cualquier
    1.28
     übernimmt
    1.27
     anunció
    1.23
    いいのか
    1.21
     ändert
    1.21
     wachsen
    1.18
     behandelt
    1.17
     erleich
    1.16
    Activations Density 0.114%

    No Known Activations