© 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. 34-GEMMASCOPE-RES-131K
    7. 106361
    Prev
    Next
    INDEX
    Explanations

    all copies or substantial portions

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     talleres
    -0.71
     JAS
    -0.69
    nombres
    -0.68
     nằm
    -0.66
    Valencia
    -0.64
     ngăn
    -0.64
     Вален
    -0.63
     prépare
    -0.63
    Nombres
    -0.63
    NextPage
    -0.62
    POSITIVE LOGITS
    ご了承ください
    0.76
     タイヤ
    0.74
    çade
    0.73
     undercut
    0.71
    ekwondo
    0.71
    czyny
    0.69
     Hentet
    0.69
    học
    0.68
    > 
    0.68
    LEAN
    0.66
    Activations Density 0.074%

    No Known Activations