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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2709
    Prev
    Next
    INDEX
    Explanations

    graphics and graphs

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

    visualized graph, computer graphics

    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_53_width_65k_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
    PreferredItem
    0.44
     জর
    0.42
    窑
    0.40
    姜
    0.40
    私募基金
    0.39
     சிலையை
    0.38
    棕
    0.37
     peacekeeping
    0.37
    朿
    0.37
    卧室
    0.37
    POSITIVE LOGITS
     graph
    4.47
     Graph
    4.16
    graph
    4.13
     graphs
    4.06
     graf
    4.03
    Graph
    4.00
     GRAPH
    3.88
     графи
    3.86
     Graphs
    3.78
     그래프
    3.75
    Activations Density 0.224%

    No Known Activations