© 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. 102623
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     these
    -1.07
     oczeki
    -0.91
    ढ
    -0.88
     będziemy
    -0.88
    🔉
    -0.87
    t
    -0.86
     welcoming
    -0.84
    prepar
    -0.83
     Caracter
    -0.83
    жне
    -0.81
    POSITIVE LOGITS
    توضیحات
    1.10
    برای
    1.05
    Daha
    1.01
    私が
    0.98
     nabízí
    0.98
    Для
    0.98
    还不错
    0.96
    สำหรับ
    0.96
    Наша
    0.96
    优秀
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.