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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116098
    Prev
    Next
    INDEX
    Explanations

    absence and sickness

    np_acts-logits-general · gemini-2.5-flash-lite

    terms related to absences, sick leave, and workplace health conditions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nyt
    -0.81
    診療
    -0.80
    videoId
    -0.77
    橄
    -0.76
    tical
    -0.73
    SEC
    -0.71
    versary
    -0.70
    SON
    -0.70
    ชาย
    -0.70
     noix
    -0.69
    POSITIVE LOGITS
     off
    1.95
     absence
    1.61
     absences
    1.48
     absent
    1.45
     absentee
    1.43
     sick
    1.39
     Absence
    1.24
     sickness
    1.23
     Abs
    1.22
    Off
    1.12
    Activations Density 0.021%

    No Known Activations