© 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
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2486
    Prev
    Next
    INDEX
    Explanations

    retrieval systems, scoring methodology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    agenda
    0.79
    Agenda
    0.73
     Agenda
    0.68
     agenda
    0.67
     общения
    0.67
    㑯
    0.67
     vicenda
    0.67
    สภาพ
    0.67
    歴
    0.65
     agendas
    0.65
    POSITIVE LOGITS
    系统
    1.61
     system
    1.54
     systems
    1.52
     devices
    1.43
    装置
    1.40
    系统的
    1.40
    系統
    1.37
     device
    1.35
    裝置
    1.34
     시스템
    1.34
    Activations Density 0.435%

    No Known Activations