© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32066
    Prev
    Next
    INDEX
    Explanations

    cleaning dishes

    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
    owitz
    -0.79
    踝
    -0.79
    legal
    -0.77
     sampel
    -0.74
    CountryCode
    -0.73
    viewer
    -0.73
    Wpf
    -0.73
     jelasnya
    -0.72
     legal
    -0.71
    inus
    -0.70
    POSITIVE LOGITS
     dish
    2.36
     washing
    2.28
     dishes
    2.20
     dishwasher
    1.98
     wash
    1.85
    洗
    1.78
     Washing
    1.77
    washing
    1.73
     Dish
    1.70
    Washing
    1.67
    Activations Density 0.009%

    No Known Activations