© 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. 114011
    Prev
    Next
    INDEX
    Explanations

    ancient names and titles

    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
     activiteiten
    -1.86
     betrekking
    -1.55
     irgendwie
    -1.48
     reacties
    -1.46
    出一个
    -1.35
    arono
    -1.34
     wenigstens
    -1.32
     najdete
    -1.31
    葙
    -1.30
    一颗
    -1.29
    POSITIVE LOGITS
     eğer
    1.36
    通过
    1.34
     wenn
    1.34
     neue
    1.34
     have
    1.34
    2
    1.30
     اگر
    1.30
     and
    1.27
     which
    1.23
     tanpa
    1.23
    Activations Density 0.012%

    No Known Activations