© 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
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10177
    Prev
    Next
    INDEX
    Explanations

    operating systems and platforms

    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
     Talent
    0.97
     villas
    0.93
    韜
    0.90
     талант
    0.89
     maxn
    0.88
    iex
    0.88
     Cedex
    0.87
     vakar
    0.87
    BackgroundTask
    0.86
     샘
    0.84
    POSITIVE LOGITS
     operating
    2.05
     Operating
    2.04
    operating
    1.95
    操作系统
    1.85
    Operating
    1.84
     OS
    1.74
     platforms
    1.64
     ОС
    1.62
    OS
    1.61
    platforms
    1.56
    Activations Density 0.443%

    No Known Activations