© 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. 58005
    Prev
    Next
    INDEX
    Explanations

    type names followed by punctuation

    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
     They
    -2.73
     如果
    -2.72
     Their
    -2.67
     comienzan
    -2.58
     Когда
    -2.36
    皲
    -2.28
     当
    -2.22
     confidentialité
    -2.20
    ⑉
    -2.19
    可以
    -2.17
    POSITIVE LOGITS
    {
    2.91
     інші
    2.50
    .
    2.39
    出一个
    2.33
    (“
    2.31
     exemples
    2.30
     твое
    2.28
    うちに
    2.27
    涐
    2.25
    asserole
    2.23
    Activations Density 0.003%

    No Known Activations