© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2089
    Prev
    Next
    INDEX
    Explanations

    home goods, office, computer, automation, repair, use

    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_17_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
     Cyr
    1.06
     انسانی
    0.91
    ală
    0.91
    Export
    0.88
    铆
    0.88
     বাল
    0.88
    的操作
    0.87
     लेफ्ट
    0.86
    ży
    0.85
    istos
    0.85
    POSITIVE LOGITS
     tangga
    1.10
    warming
    1.07
    ostatic
    0.94
    鄉
    0.89
    coming
    0.89
     clos
    0.88
    乡
    0.87
     chores
    0.86
    wares
    0.86
     consumption
    0.85
    Activations Density 0.416%

    No Known Activations