© 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. 3415
    Prev
    Next
    INDEX
    Explanations

    identification papers and licenses

    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
    бата
    -0.83
     Politique
    -0.82
    ESG
    -0.69
    före
    -0.69
    ratislava
    -0.69
     Fuerza
    -0.69
    卐
    -0.69
    зон
    -0.69
     leste
    -0.69
     Desenvolvimento
    -0.68
    POSITIVE LOGITS
     driver
    3.70
     drivers
    3.39
     Drivers
    3.08
     Driver
    3.02
    driver
    3.02
    Driver
    2.80
    Drivers
    2.78
     driving
    2.73
    drivers
    2.72
     passport
    2.41
    Activations Density 0.051%

    No Known Activations