© 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. 70344
    Prev
    Next
    INDEX
    Explanations

    closing quotation marks and apostrophes

    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
    攫
    -1.63
    这是一
    -1.58
     a
    -1.55
     We
    -1.41
    体重
    -1.35
    .~\
    -1.34
     leven
    -1.32
    眉毛
    -1.31
     then
    -1.30
    )_
    -1.27
    POSITIVE LOGITS
     new
    1.61
     любы
    1.60
     promociones
    1.49
     would
    1.38
    mẫu
    1.35
    樁
    1.34
    gencias
    1.34
     only
    1.33
     nowych
    1.32
     wraz
    1.31
    Activations Density 0.071%

    No Known Activations