© 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. 22-GEMMASCOPE-RES-131K
    7. 32870
    Prev
    Next
    INDEX
    Explanations

    numbers and specific list items

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    (''
    -0.77
     it
    -0.77
     task
    -0.75
    向了
    -0.75
     with
    -0.73
     tasks
    -0.72
    此前
    -0.72
    wares
    -0.71
     tools
    -0.71
    さらに
    -0.70
    POSITIVE LOGITS
     avancer
    0.92
     profonde
    0.92
     iny
    0.92
    歺
    0.90
     oub
    0.89
    红的
    0.88
     ansatte
    0.87
    Political
    0.87
    OCTOBER
    0.85
     souvent
    0.85
    Activations Density 0.070%

    No Known Activations