© 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. 10-GEMMASCOPE-RES-131K
    7. 86953
    Prev
    Next
    INDEX
    Explanations

    user data and groups

    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
    饪
    -2.47
    舠
    -2.05
    馓
    -2.03
    坶
    -1.99
    sandalia
    -1.93
     is
    -1.91
    oucí
    -1.87
    //(
    -1.86
    鐃
    -1.84
    èvent
    -1.84
    POSITIVE LOGITS
    撷
    2.34
     contemporáneo
    2.00
     literaria
    1.83
     extraordinario
    1.81
     บาง
    1.77
    开玩笑
    1.73
     
    1.70
    crire
    1.69
     ‘‘
    1.68
    ようですが
    1.68
    Activations Density 0.004%

    No Known Activations