© 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. 83630
    Prev
    Next
    INDEX
    Explanations

    dimensions of objects

    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
    蠓
    -1.73
     was
    -1.59
     gând
    -1.58
     decât
    -1.57
    萑
    -1.56
     redacción
    -1.54
    瓩
    -1.54
     așa
    -1.53
     îmb
    -1.50
     răsp
    -1.48
    POSITIVE LOGITS
    沨
    1.76
     Vorteil
    1.66
    ՝
    1.62
    嗚
    1.56
     terlaris
    1.52
    様々な
    1.50
     leſs
    1.50
    ciri
    1.47
     Geschä
    1.47
    Interestingly
    1.46
    Activations Density 0.019%

    No Known Activations