© 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. 58166
    Prev
    Next
    INDEX
    Explanations

    cars and car brands

    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
    あなた
    -1.39
    外出
    -1.35
    大阪
    -1.30
    あなたは
    -1.28
    あなたが
    -1.27
     gitt
    -1.27
    　　（
    -1.24
     nying
    -1.23
     murales
    -1.20
    endDate
    -1.19
    POSITIVE LOGITS
     obtenidos
    1.48
    urbo
    1.34
     cihaz
    1.34
    都想
    1.31
     всех
    1.30
     será
    1.29
    いっぱい
    1.27
     seleccionados
    1.25
    vallis
    1.25
     başlad
    1.24
    Activations Density 0.024%

    No Known Activations