© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11522
    Prev
    Next
    INDEX
    Explanations

    UI components

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

    reusable components and code

    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
    ContextProvider
    0.43
     پل
    0.42
     ஏற்படுத்து
    0.40
    麒
    0.39
    mapi
    0.39
     तुमसे
    0.38
    wein
    0.38
    鍱
    0.38
    พล
    0.38
     KEYS
    0.37
    POSITIVE LOGITS
     components
    0.98
     componente
    0.96
     component
    0.95
     componentes
    0.95
    component
    0.93
     компонентов
    0.91
     komponen
    0.88
     компонен
    0.87
     komponent
    0.87
     componenti
    0.86
    Activations Density 0.023%

    No Known Activations