© 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. 1825
    Prev
    Next
    INDEX
    Explanations

    await db

    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
     stove
    1.29
     ша
    1.29
    ㅡ
    1.26
     স
    1.24
     parse
    1.23
     ١
    1.22
     وش
    1.22
     ٢
    1.22
     Payable
    1.21
     Frame
    1.21
    POSITIVE LOGITS
    พร้อม
    0.81
    শ্রেষ্ঠ
    0.81
    est
    0.80
    その他
    0.78
     comparación
    0.78
    èrent
    0.77
    新型コロナ
    0.75
     disponibilités
    0.75
     ndị
    0.74
     desconoc
    0.74
    Activations Density 0.730%

    No Known Activations