© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10620
    Prev
    Next
    INDEX
    Explanations

    stocks, double play, Chinese high, Pandora had, bolster China, Cessna pilot, compile database, Chess is, Korean audience

    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
    𐰼
    1.45
    n
    1.40
    vý
    1.31
    lava
    1.27
    nY
    1.24
    టర్‌
    1.23
    人气
    1.21
    opera
    1.17
    vagrant
    1.17
    la
    1.15
    POSITIVE LOGITS
    ي
    1.31
    ))
    1.29
     clickable
    1.23
    <unused89>
    1.17
     asterisk
    1.13
     spacing
    1.13
     applicable
    1.12
    ignement
    1.11
     inconsider
    1.11
     대해서
    1.09
    Activations Density 0.007%

    No Known Activations