© 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. 59365
    Prev
    Next
    INDEX
    Explanations

    Names of people or places

    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
    寕
    -3.23
    䉴
    -2.91
    
    -2.88
    䊉
    -2.70
    觧
    -2.64
    鹋
    -2.58
    囖
    -2.56
    
    -2.55
    撄
    -2.55
    ”،
    -2.55
    POSITIVE LOGITS
     When
    3.17
    ’
    3.13
    {
    2.89
     There
    2.67
    {
    2.53
    ";
    2.50
     While
    2.50
     Does
    2.41
     During
    2.38
    </strong>
    2.36
    Activations Density 0.028%

    No Known Activations