© 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. 61347
    Prev
    Next
    INDEX
    Explanations

    winding, wound, wind

    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
    .
    -2.69
    ,’
    -2.56
    的人都
    -2.56
    ”
    -2.56
     あります
    -2.52
    小孩子
    -2.48
    
    -2.47
     häufigsten
    -2.44
    '
    -2.42
    偏偏
    -2.41
    POSITIVE LOGITS
    ⦊
    2.91
    ﻊ
    2.86
    柃
    2.70
    ～～
    2.66
     techniczne
    2.56
     intellectuelle
    2.52
    𓆜
    2.47
     resolute
    2.44
     präsenti
    2.42
     contemplative
    2.41
    Activations Density 0.011%

    No Known Activations