© 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. 45675
    Prev
    Next
    INDEX
    Explanations

    integrals starting with 0 `_`

    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
     Membuat
    -1.71
     übri
    -1.63
    )$.
    -1.60
    一旦
    -1.59
    你要
    -1.59
    ↵
    -1.57
     advise
    -1.55
    vertreter
    -1.54
     gesamte
    -1.53
     mettere
    -1.53
    POSITIVE LOGITS
    </h5>
    1.72
     It
    1.64
    </h4>
    1.51
    \
    1.48
    鳙
    1.46
     şi
    1.45
     poupée
    1.39
    锉
    1.37
     L
    1.37
    </h3>
    1.37
    Activations Density 0.006%

    No Known Activations