© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 22956
    Prev
    Next
    INDEX
    Explanations

    sick leave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    座
    0.50
    ปี
    0.47
    ్ఞ
    0.46
     insuff
    0.43
    ãi
    0.43
     UNNEEDED
    0.43
    ОР
    0.43
     ĝi
    0.42
    炎
    0.42
     произо
    0.42
    POSITIVE LOGITS
     sick
    0.91
     Sick
    0.89
    Sick
    0.82
    sick
    0.70
     unwell
    0.62
     sickness
    0.60
     ill
    0.59
     बीमार
    0.57
     অসুস্থ
    0.56
     enfermo
    0.56
    Activations Density 0.001%

    No Known Activations