© 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. 22-GEMMASCOPE-RES-131K
    7. 127734
    Prev
    Next
    INDEX
    Explanations

    School or Department of

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    これ
    -1.53
     Substanz
    -1.47
    と思い
    -1.43
     dunklen
    -1.43
    なぜ
    -1.41
     acoged
    -1.40
    商品は
    -1.40
    すべて
    -1.38
    これは
    -1.38
    。　
    -1.38
    POSITIVE LOGITS
     of
    4.88
    ようになります
    1.65
    為に
    1.56
    înt
    1.48
    Então
    1.43
    ját
    1.41
    škas
    1.41
     nadru
    1.39
     gedachten
    1.38
    okra
    1.35
    Activations Density 0.069%

    No Known Activations