© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1782
    Prev
    Next
    INDEX
    Explanations

    summarizing and explaining meaning

    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_13_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
    ↵↵
    1.33
     simult
    1.09
     pull
    1.08
     第一
    1.06
     typ
    1.06
     (
    1.05
     First
    1.04
     通常
    1.03
     ●
    1.01
     pr
    1.00
    POSITIVE LOGITS
    Lastly
    1.66
    Enfin
    1.61
    Finalmente
    1.52
     lastly
    1.51
     infine
    1.45
    Finally
    1.44
    Concluding
    1.38
    Conclusion
    1.37
    最後に
    1.35
    finally
    1.35
    Activations Density 0.539%

    No Known Activations