© 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. 47135
    Prev
    Next
    INDEX
    Explanations

    setting up systems

    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
    alsh
    -0.86
     着
    -0.82
    ávajú
    -0.82
     contienen
    -0.80
    kontak
    -0.78
    getService
    -0.77
    ICIENCY
    -0.77
    贯
    -0.76
    汽車
    -0.76
     Վեր
    -0.75
    POSITIVE LOGITS
     setup
    6.41
    setup
    4.81
     setups
    4.59
     Setup
    4.47
    Setup
    4.31
     SETUP
    3.84
    SETUP
    3.52
     arrangement
    3.42
     configuration
    3.27
    setu
    2.89
    Activations Density 0.170%

    No Known Activations