© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1947
    Prev
    Next
    INDEX
    Explanations

    why and how introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     badass
    1.21
     ALSO
    1.17
     FYI
    1.16
     naughty
    1.13
     soooo
    1.11
     ____
    1.11
     sooo
    1.10
     那
    1.10
     crappy
    1.10
     그거
    1.09
    POSITIVE LOGITS
    Figure
    1.49
    Discussion
    1.34
    Table
    1.34
    Fig
    1.31
    Conversion
    1.31
    Conclusion
    1.30
    
    1.29
    Definition
    1.28
    Page
    1.28
    Definitions
    1.27
    Activations Density 0.176%

    No Known Activations