© 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. 15794
    Prev
    Next
    INDEX
    Explanations

    type identifier

    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
     that
    -1.83
    但不
    -1.39
    ي
    -1.27
    而
    -1.26
    </strong>
    -1.23
     bekämp
    -1.23
    الا
    -1.20
    Мы
    -1.19
    Testimonials
    -1.18
     času
    -1.16
    POSITIVE LOGITS
    AfterViewInit
    1.48
     digitale
    1.34
     SqlCommand
    1.33
    屋さん
    1.31
     maximale
    1.30
     lande
    1.30
    ække
    1.29
     onFailure
    1.27
     optimale
    1.27
    にしました
    1.26
    Activations Density 0.019%

    No Known Activations