© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15887
    Prev
    Next
    INDEX
    Explanations

    starting servers and processes

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

    server start and run

    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_31_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
     imagenes
    0.52
     Imágenes
    0.50
     imagens
    0.49
    redux
    0.48
     reducer
    0.47
     images
    0.46
     recipient
    0.46
    ໊
    0.46
     Amn
    0.45
     ලබා
    0.44
    POSITIVE LOGITS
    ServerSocket
    0.50
    ListenAndServe
    0.47
    startup
    0.41
    icularis
    0.41
    щей
    0.41
     स्टार्ट
    0.40
    Started
    0.40
    Steady
    0.39
     startDate
    0.39
    Animator
    0.39
    Activations Density 0.023%

    No Known Activations