© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68663
    Prev
    Next
    INDEX
    Explanations

    mileage and mathematical notation

    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
    Negative Logits
    </h2>
    -3.19
     With
    -2.66
     Through
    -2.61
     However
    -2.53
     Sadly
    -2.42
     Unfortunately
    -2.34
     exquisitely
    -2.34
     After
    -2.34
     During
    -2.33
     Using
    -2.31
    POSITIVE LOGITS
    驁
    2.53
    艄
    2.45
    嘡
    2.41
    
    2.23
     komplette
    2.23
     manj
    2.22
    找个
    2.20
    ⑊
    2.20
     branco
    2.19
    鬭
    2.19
    Activations Density 0.003%

    No Known Activations