© 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. 10-GEMMASCOPE-RES-131K
    7. 14664
    Prev
    Next
    INDEX
    Explanations

    html closing tags

    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
     But
    -2.83
    y
    -2.55
    焄
    -2.52
     แต่
    -2.47
      
    -2.38
    ↵
    -2.23
    
    -2.22
    <i>
    -2.20
     ligeramente
    -2.19
     &
    -2.17
    POSITIVE LOGITS
    ations
    2.92
    嫺
    2.61
    鏐
    2.39
    姸
    2.33
    諶
    2.33
    鼴
    2.31
     \_
    2.30
    蘩
    2.28
    鼱
    2.27
    \
    2.25
    Activations Density 0.003%

    No Known Activations