© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8699
    Prev
    Next
    INDEX
    Explanations

    key features, main points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
    oggles
    0.97
    EDGE
    0.96
    奇怪
    0.95
    ẫ
    0.94
    ̕
    0.92
    翳
    0.90
    ၀၀
    0.89
    質問
    0.89
     Suddenly
    0.89
    oggle
    0.88
    POSITIVE LOGITS
     main
    4.21
    main
    3.87
     MAIN
    3.75
    Main
    3.70
     principale
    3.58
     Main
    3.57
    MAIN
    3.50
     principal
    3.40
     principali
    3.35
     principais
    3.28
    Activations Density 0.369%

    No Known Activations