© 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. 66541
    Prev
    Next
    INDEX
    Explanations

    web component tags

    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
     to
    -2.20
    几天
    -1.41
     It
    -1.41
    开玩笑
    -1.40
     \
    -1.35
     you
    -1.34
     because
    -1.32
     ۲۵
    -1.31
    mountable
    -1.31
     we
    -1.30
    POSITIVE LOGITS
     continuare
    1.63
    Добавлено
    1.52
    鮡
    1.51
     almohada
    1.43
    遄
    1.40
     laajenta
    1.39
    asının
    1.38
     NEEDED
    1.38
    糴
    1.38
    了吧
    1.37
    Activations Density 0.024%

    No Known Activations