© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 989
    Prev
    Next
    INDEX
    Explanations

    charms

    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
    <s>
    0.94
    ’
    0.90
    cit
    0.84
    fl
    0.83
    gener
    0.83
    says
    0.83
    ndash
    0.82
    €™
    0.81
    their
    0.81
    donation
    0.81
    POSITIVE LOGITS
     Note
    1.66
     Copyright
    1.65
     Summary
    1.58
     References
    1.57
     Notes
    1.56
     Disclaimer
    1.48
     SUMMARY
    1.47
     Introduction
    1.44
     NOTE
    1.44
     Contents
    1.40
    Activations Density 0.967%

    No Known Activations