© 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. 106844
    Prev
    Next
    INDEX
    Explanations

    hot drinks

    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
     sunscreen
    -0.80
     Crystal
    -0.75
    欖
    -0.74
    Crystal
    -0.74
     cigarettes
    -0.72
    午餐
    -0.71
    bca
    -0.71
     konst
    -0.71
    йо
    -0.69
    bach
    -0.69
    POSITIVE LOGITS
     hot
    1.98
     cocoa
    1.72
     Hot
    1.66
    Hot
    1.48
    hot
    1.38
    HOT
    1.34
     warming
    1.22
     sıcak
    1.21
    ホット
    1.21
     drink
    1.20
    Activations Density 0.013%

    No Known Activations