© 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. 6738
    Prev
    Next
    INDEX
    Explanations

    non-english words

    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
     its
    -1.59
     such
    -1.52
     how
    -1.45
     itself
    -1.37
     among
    -1.37
     infolge
    -1.34
     at
    -1.33
     from
    -1.33
     like
    -1.30
     shows
    -1.28
    POSITIVE LOGITS
     mètres
    1.38
     världen
    1.34
     блюдо
    1.34
    şey
    1.34
    tikai
    1.30
     لأنه
    1.28
    🍚
    1.27
     الأخيرة
    1.26
     teorías
    1.23
    springen
    1.20
    Activations Density 0.485%

    No Known Activations