© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84864
    Prev
    Next
    INDEX
    Explanations

    home appliances

    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
     dAtA
    -0.93
     CITES
    -0.85
     Opto
    -0.80
    烯
    -0.79
     parro
    -0.79
     opto
    -0.79
     nutty
    -0.77
    öd
    -0.77
     dusty
    -0.77
    骶
    -0.75
    POSITIVE LOGITS
     appliance
    1.48
     Appliance
    1.31
     appliances
    1.18
     Kitchen
    1.18
     dishwasher
    1.15
     washer
    1.14
    cooking
    1.09
     Whirlpool
    1.08
    kitchen
    1.07
    cook
    1.05
    Activations Density 0.028%

    No Known Activations