© 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. 106222
    Prev
    Next
    INDEX
    Explanations

    P.O. Box addresses

    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
     see
    -0.77
    Keller
    -0.76
    一方で
    -0.73
    ènements
    -0.72
    autoreleasepool
    -0.72
     achieved
    -0.68
     operating
    -0.67
     approve
    -0.67
     посмотреть
    -0.67
    Straße
    -0.66
    POSITIVE LOGITS
     Box
    2.91
     box
    2.80
    Box
    2.56
     BOX
    2.36
    box
    2.36
    BOX
    2.13
     boxes
    2.11
     Boxes
    2.06
    boxes
    1.70
    Boxes
    1.61
    Activations Density 0.004%

    No Known Activations