© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 861
    Prev
    Next
    INDEX
    Explanations

    states and transitions

    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
    ﾇ
    2.39
     書い
    2.11
    ჲ
    2.09
     聞い
    2.08
     剤
    2.08
     行っ
    2.07
     遊ん
    2.07
     ბ
    2.07
     ショルダー
    2.03
     また
    2.02
    POSITIVE LOGITS
     các
    3.59
     không
    3.41
     của
    3.24
     đã
    3.19
     cùng
    3.10
     thông
    3.07
     và
    3.06
     được
    3.05
     từ
    3.05
     bên
    3.05
    Activations Density 0.018%

    No Known Activations