© 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. 68516
    Prev
    Next
    INDEX
    Explanations

    due, required, necessary, possible

    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
     recepto
    -1.40
     this
    -1.36
     laba
    -1.30
     labd
    -1.25
    エディ
    -1.24
     frustra
    -1.23
     recherche
    -1.23
    哢
    -1.23
     kni
    -1.23
    رر
    -1.22
    POSITIVE LOGITS
     после
    1.37
     após
    1.25
     after
    1.24
    ينا
    1.23
    しました
    1.23
    cution
    1.16
     بعد
    1.15
    Ligações
    1.13
     как
    1.11
     estrelas
    1.10
    Activations Density 0.111%

    No Known Activations