© 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. 22793
    Prev
    Next
    INDEX
    Explanations

    angular js services and scope

    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
    either
    -1.66
     either
    -1.54
    </sub>
    -1.45
     was
    -1.45
    叕
    -1.38
     Either
    -1.34
     pozwala
    -1.34
    Magick
    -1.33
    ᴎ
    -1.32
     deko
    -1.30
    POSITIVE LOGITS
    </em>
    1.95
     Spherical
    1.32
    S
    1.31
     estadual
    1.18
    G
    1.17
    變化
    1.17
     cudd
    1.16
     nieruchomości
    1.15
    おはよう
    1.13
     неда
    1.13
    Activations Density 0.042%

    No Known Activations