© 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. 68520
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
     then
    -1.44
     something
    -1.43
     séjours
    -1.32
     fogo
    -1.30
     السياس
    -1.30
     you
    -1.30
    쨩
    -1.30
    
    -1.29
     правительства
    -1.29
    ੨
    -1.27
    POSITIVE LOGITS
     ημέ
    1.41
     hoffen
    1.30
     Unfortunately
    1.30
     рецепта
    1.30
    олові
    1.27
     यदि
    1.27
     comté
    1.23
    жества
    1.21
     Пока
    1.20
     pican
    1.18
    Activations Density 0.055%

    No Known Activations