© 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. 33793
    Prev
    Next
    INDEX
    Explanations

    dining room

    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
    Дети
    -0.86
    mbolos
    -0.81
     shutout
    -0.79
    useum
    -0.77
     preoccup
    -0.76
    Шу
    -0.75
    IVITY
    -0.75
    🏢
    -0.75
    ▰
    -0.74
     salada
    -0.74
    POSITIVE LOGITS
     eating
    1.99
     dining
    1.92
     eat
    1.80
     breakfast
    1.60
    eating
    1.59
     Eating
    1.57
     din
    1.53
    Eating
    1.46
     Eat
    1.39
     Dining
    1.37
    Activations Density 0.011%

    No Known Activations