© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90795
    Prev
    Next
    INDEX
    Explanations

    backgrounds, miserable, told, wheel, doing, text

    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
    Not in Any Lists

    No Comments

    Negative Logits
     både
    -2.73
    providedIn
    -2.50
    
    -2.31
    饽
    -2.28
    ๖
    -2.28
    ofa
    -2.22
     ò
    -2.19
     plupart
    -2.19
    先是
    -2.16
    ▣
    -2.14
    POSITIVE LOGITS
     whatnot
    3.23
     then
    2.94
    \
    2.86
    しました
    2.78
    amp
    2.66
    z
    2.59
    This
    2.50
     sebagainya
    2.48
    n
    2.45
    c
    2.44
    Activations Density 0.027%

    No Known Activations