© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14541
    Prev
    Next
    INDEX
    Explanations

    Q/A formats or specific answers

    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_22/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
    ۔
    -1.46
    spania
    -1.41
     ہیں۔
    -1.35
     通り
    -1.30
    龵
    -1.23
     its
    -1.21
    файл
    -1.20
     داره
    -1.17
    さんで
    -1.16
    octanol
    -1.13
    POSITIVE LOGITS
     ซึ่ง
    1.39
    场比赛
    1.34
     unangemessene
    1.28
     essas
    1.21
    この
    1.20
    Caracteristici
    1.20
     partag
    1.17
     déclar
    1.17
    Fotografía
    1.16
     ทั้ง
    1.16
    Activations Density 0.000%

    No Known Activations