© 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. 84163
    Prev
    Next
    INDEX
    Explanations

    bedroom furniture and features

    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
     kitchen
    -0.96
    kitchen
    -0.95
    Kitchen
    -0.89
     kitchens
    -0.88
    seats
    -0.84
     кухо
    -0.83
    basement
    -0.82
     kindergarten
    -0.81
    salon
    -0.81
    adm
    -0.81
    POSITIVE LOGITS
     bedside
    2.55
     headboard
    1.79
     bed
    1.62
     dresser
    1.45
    床
    1.41
     night
    1.39
     bedroom
    1.34
    Bed
    1.33
     Bed
    1.30
     closet
    1.30
    Activations Density 0.015%

    No Known Activations