© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9029
    Prev
    Next
    INDEX
    Explanations

    App.Config or MainWindow.ViewModel

    np_acts-logits-general · gemini-2.5-flash-lite

    main app component file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     苏
    0.43
    richtungen
    0.43
    பெரு
    0.41
    entwick
    0.40
    flare
    0.39
    affin
    0.39
    蘇
    0.39
    ლება
    0.38
    могою
    0.38
     জড়ের
    0.38
    POSITIVE LOGITS
    цова
    0.39
     সমন্ব
    0.37
     प्रणाम
    0.37
     scoped
    0.37
     весь
    0.37
     nel
    0.36
    尿
    0.36
    痰
    0.36
    ерт
    0.36
     أع
    0.35
    Activations Density 0.002%

    No Known Activations