© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1898
    Prev
    Next
    INDEX
    Explanations

    refrigerator

    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
    ユニ
    -0.79
     heating
    -0.74
    安全的
    -0.73
    פה
    -0.70
     heated
    -0.70
    riterion
    -0.69
    ття
    -0.69
     wunderbar
    -0.69
    Pon
    -0.68
    ЦИИ
    -0.68
    POSITIVE LOGITS
     refrigerator
    1.34
     fridge
    1.27
     refrigerators
    1.21
    Refriger
    1.06
     refrigerate
    1.03
     Refriger
    1.02
     холоди
    1.00
    冷蔵庫
    0.98
     Refrigerator
    0.97
     Side
    0.96
    Activations Density 0.017%

    No Known Activations