© 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. 22739
    Prev
    Next
    INDEX
    Explanations

    names

    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
    raszam
    -1.38
     vecka
    -1.32
    جمعیت
    -1.31
     célè
    -1.29
    襯
    -1.28
    ことは
    -1.26
    itchfield
    -1.25
     onsdag
    -1.23
    才會
    -1.23
     dziś
    -1.23
    POSITIVE LOGITS
     a
    1.70
     to
    1.63
    ৄ
    1.60
     as
    1.40
     Instead
    1.38
    咄
    1.32
    ーラー
    1.31
     problemas
    1.30
    ());
    1.29
    sebagai
    1.28
    Activations Density 0.105%

    No Known Activations