© 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. 6669
    Prev
    Next
    INDEX
    Explanations

    Cross Country

    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
    ://
    -1.17
     Why
    -1.16
    ()
    -1.14
     bouillon
    -1.13
      
    -1.11
    шает
    -1.11
     Anyone
    -1.10
     штука
    -1.10
     характеристики
    -1.09
    le
    -1.08
    POSITIVE LOGITS
     chercheurs
    1.41
    yeni
    1.37
     including
    1.34
     pomaga
    1.34
    AntiForgery
    1.34
    lcccc
    1.30
    Einzel
    1.30
     amarillas
    1.29
    immen
    1.27
    siębior
    1.27
    Activations Density 0.000%

    No Known Activations