© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64689
    Prev
    Next
    INDEX
    Explanations

    relative paths to utilities

    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
    Not in Any Lists

    No Comments

    Negative Logits
     today
    -0.82
     představ
    -0.81
    dibujos
    -0.78
    有料
    -0.78
    Фар
    -0.77
     hides
    -0.76
    Виды
    -0.75
    Симпто
    -0.74
    rspec
    -0.73
    salle
    -0.73
    POSITIVE LOGITS
     utils
    2.44
    utils
    2.36
    util
    2.05
     Utils
    2.03
     utilities
    1.96
     utility
    1.96
     util
    1.87
    Utils
    1.86
    common
    1.73
     Util
    1.70
    Activations Density 0.045%

    No Known Activations