© 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. 47177
    Prev
    Next
    INDEX
    Explanations

    command line tools

    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
     folhe
    -1.10
     escritório
    -1.09
     começo
    -1.06
     juzgar
    -1.04
     relógio
    -1.04
     artesanato
    -1.02
     essas
    -1.00
     exercício
    -1.00
     primeiro
    -0.99
     obtenu
    -0.99
    POSITIVE LOGITS
     so
    1.05
    |--
    1.05
     all
    1.02
     –
    0.98
     tertawa
    0.96
     Tämä
    0.94
     ALL
    0.90
     vur
    0.90
    หน้าน
    0.89
    publicPath
    0.88
    Activations Density 0.046%

    No Known Activations