© 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. 38057
    Prev
    Next
    INDEX
    Explanations

    refrigerator or fridge

    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
    电池
    -0.74
    factory
    -0.73
     underscore
    -0.73
    LOGOUT
    -0.72
    entas
    -0.72
    IRO
    -0.69
    шков
    -0.68
    Ẵ
    -0.68
    ächlich
    -0.68
    rung
    -0.68
    POSITIVE LOGITS
     fridge
    5.09
     refrigerator
    4.91
     refrigerators
    3.77
     Fridge
    3.50
    refriger
    3.33
     Refrigerator
    3.27
     холоди
    3.19
    Refriger
    2.98
    冷蔵庫
    2.98
    冰箱
    2.92
    Activations Density 0.031%

    No Known Activations