© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8746
    Prev
    Next
    INDEX
    Explanations

    restaurants, cafes, shops

    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_10/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
    𖣘
    -1.88
    Often
    -1.85
    They
    -1.84
    Sometimes
    -1.74
     が
    -1.68
    Even
    -1.63
    ࿚
    -1.61
     With
    -1.59
     иногда
    -1.59
    Being
    -1.56
    POSITIVE LOGITS
    Restaurants
    2.28
    蚡
    2.20
    restaurants
    1.98
     restaurants
    1.91
    簠
    1.77
     Restaurants
    1.75
    鹛
    1.75
    蔸
    1.73
    鑁
    1.66
    鬭
    1.66
    Activations Density 0.018%

    No Known Activations