© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11827
    Prev
    Next
    INDEX
    Explanations

    knights and orders

    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
     Geden
    -0.82
     BISHOP
    -0.76
     Grä
    -0.75
    strata
    -0.74
    管道
    -0.72
     точку
    -0.71
    fili
    -0.71
     onlyOwner
    -0.70
     Bibel
    -0.70
     conditions
    -0.69
    POSITIVE LOGITS
     Knights
    1.64
     knights
    1.57
    Knights
    1.38
    Knight
    1.36
     Knight
    1.36
     knight
    1.36
     Order
    1.23
    騎士
    1.21
    Order
    1.13
     Hosp
    1.13
    Activations Density 0.017%

    No Known Activations