© 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. 39663
    Prev
    Next
    INDEX
    Explanations

    kn prefix words

    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
    Ꮟ
    -2.78
    e
    -2.77
    ༑
    -2.55
    蹀
    -2.53
    s
    -2.48
    ༈
    -2.44
    鏨
    -2.42
    Привет
    -2.39
    Ошибка
    -2.36
    ＾
    -2.36
    POSITIVE LOGITS
    '
    4.13
     và
    2.52
    ৢ
    2.47
    嵎
    2.45
     však
    2.44
     puede
    2.42
    section
    2.28
     será
    2.23
     \&
    2.22
    ?"
    2.19
    Activations Density 0.001%

    No Known Activations