© 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. 70031
    Prev
    Next
    INDEX
    Explanations

    laundry and washing

    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
    Blurb
    -0.73
     Mistress
    -0.73
     LITERATURE
    -0.71
    NVIDIA
    -0.69
    Diction
    -0.69
     Sleeps
    -0.69
    Wrist
    -0.69
    <0xAC>
    -0.68
     карьера
    -0.68
    瓣
    -0.68
    POSITIVE LOGITS
     laundry
    4.34
     Laundry
    3.39
    Laundry
    3.03
    laundry
    3.02
     washer
    2.84
     washing
    2.47
    洗濯
    2.28
     laund
    2.28
     Washer
    2.28
    洗衣
    2.25
    Activations Density 0.015%

    No Known Activations