© 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. 38613
    Prev
    Next
    INDEX
    Explanations

    spaces

    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
    あるので
    -2.70
    it
    -2.66
    あります
    -2.55
    K
    -2.47
     avec
    -2.44
    </b>
    -2.41
    D
    -2.39
    L
    -2.30
    .
    -2.28
     were
    -2.20
    POSITIVE LOGITS
    鬭
    2.48
    عنی
    2.45
    ността
    2.42
    leggio
    2.30
     Then
    2.27
    ⁧
    2.17
    廡
    2.16
    鹩
    2.14
    vantaged
    2.13
    ðsíða
    2.11
    Activations Density 0.013%

    No Known Activations