© 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. 109650
    Prev
    Next
    INDEX
    Explanations

    household chores and homemaking

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ジック
    -0.81
     Mitarbeiter
    -0.80
    omb
    -0.80
    轻易
    -0.79
    السكان
    -0.78
    PTION
    -0.77
     ''){
    -0.77
     människor
    -0.77
     malpractice
    -0.77
    惋
    -0.77
    POSITIVE LOGITS
     chores
    3.27
     tasks
    2.83
     housework
    2.52
     household
    2.30
     cleaning
    2.22
     chore
    2.17
    tasks
    2.16
    Tasks
    2.02
     task
    2.02
    cleaning
    2.00
    Activations Density 0.042%

    No Known Activations