© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15487
    Prev
    Next
    INDEX
    Explanations

    speak in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    1.26
    м
    1.13
    ियों
    1.04
    いずれ
    1.02
    ্টি
    1.00
    дная
    0.98
    ️⃣
    0.97
     প্রাচ
    0.94
     llegar
    0.94
    줍
    0.94
    POSITIVE LOGITS
     faith
    1.14
    ⅓
    1.14
    ыска
    1.09
     cur
    1.07
     subcontractors
    1.06
     एक्सपे
    1.06
     vassals
    1.06
     landowners
    1.05
     জড়িত
    1.03
     equator
    1.03
    Activations Density 0.002%

    No Known Activations