© 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. 71767
    Prev
    Next
    INDEX
    Explanations

    code block terminators

    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
    )),
    -1.49
    旆
    -1.41
     nuestros
    -1.41
    들의
    -1.41
    ‌هایی
    -1.40
    Notae
    -1.38
     nuestras
    -1.38
    ᥬ
    -1.37
    leč
    -1.36
     hayan
    -1.35
    POSITIVE LOGITS
    ↵↵
    1.73
    U
    1.35
     również
    1.35
     пользователем
    1.32
     ebenfalls
    1.31
     regarding
    1.31
     ベクトル
    1.31
    ಸ್
    1.30
     fortfarande
    1.27
    一样
    1.27
    Activations Density 0.167%

    No Known Activations