© 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. 45411
    Prev
    Next
    INDEX
    Explanations

    legal, technical, and foreign terms

    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
     then
    -1.28
     but
    -1.23
     it
    -1.23
     sogar
    -1.20
    diendo
    -1.15
     sosis
    -1.14
     even
    -1.14
    Jae
    -1.11
    就已经
    -1.11
     siya
    -1.09
    POSITIVE LOGITS
     estrenar
    1.74
     помню
    1.48
    も行
    1.38
     одной
    1.37
     atualizar
    1.35
    </strong>
    1.34
    に行ってきました
    1.32
    uacute
    1.32
     trám
    1.30
     女生
    1.29
    Activations Density 1.160%

    No Known Activations