© 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. 47012
    Prev
    Next
    INDEX
    Explanations

    numbers and symbolic separators

    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
     vare
    -0.89
     ito
    -0.78
     afe
    -0.71
    feasible
    -0.71
     ils
    -0.71
    Abdul
    -0.70
     Zheng
    -0.70
    fullscreen
    -0.70
     Abdul
    -0.69
     sut
    -0.67
    POSITIVE LOGITS
    Twelve
    0.88
     Twelve
    0.80
     twelve
    0.78
     decirle
    0.75
    Liu
    0.73
    cer
    0.73
    മ
    0.72
    kering
    0.71
    Eight
    0.71
     dipped
    0.70
    Activations Density 0.315%

    No Known Activations