© 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. 83816
    Prev
    Next
    INDEX
    Explanations

    paths and programming identifiers

    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
     the
    -3.14
     voor
    -2.91
     unparalleled
    -2.84
    quelize
    -2.83
    曁
    -2.67
     für
    -2.66
    _
    -2.66
    廝
    -2.66
    ၟ
    -2.58
     برای
    -2.53
    POSITIVE LOGITS
    揠
    2.91
     &
    2.78
     шесть
    2.70
    再多
    2.59
    ༀ
    2.56
    缡
    2.55
     пять
    2.53
    苙
    2.47
     девя
    2.45
     monstrous
    2.44
    Activations Density 0.100%

    No Known Activations