© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30627
    Prev
    Next
    INDEX
    Explanations

    "knight" as part of proper names and titles

    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
     wund
    -0.88
     Filename
    -0.85
    ==='
    -0.79
     syntactic
    -0.78
     Կ
    -0.77
     comprehend
    -0.76
     Earrings
    -0.71
    ukkah
    -0.70
     weeds
    -0.70
     Taxation
    -0.69
    POSITIVE LOGITS
     Templar
    1.30
    ingale
    1.14
    mare
    0.96
    ly
    0.95
     Err
    0.95
     shift
    0.91
    Knight
    0.91
     tem
    0.90
     Kn
    0.90
     Knight
    0.89
    Activations Density 0.006%

    No Known Activations