© 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. 13534
    Prev
    Next
    INDEX
    Explanations

    closing quotes and parentheses

    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
    𖣘
    -1.90
     deutscher
    -1.86
     женщины
    -1.78
    --"
    -1.66
    ꜆
    -1.61
    ("
    -1.61
     allemand
    -1.55
    嵓
    -1.54
     parfü
    -1.54
     THEY
    -1.53
    POSITIVE LOGITS
     we
    2.02
    días
    1.80
     in
    1.67
    ynı
    1.66
    ?”
    1.66
    ”,
    1.60
     Both
    1.59
    ’
    1.55
    grafías
    1.54
    ícias
    1.53
    Activations Density 0.029%

    No Known Activations