© 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. 47742
    Prev
    Next
    INDEX
    Explanations

    Buddhist teachings and figures

    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
    Salem
    -1.05
    Bible
    -1.03
     MATLAB
    -0.99
    ‾
    -0.99
    Cas
    -0.96
     خدا
    -0.96
    geschäft
    -0.96
     Cré
    -0.93
    figcaption
    -0.93
    Baker
    -0.91
    POSITIVE LOGITS
     Buddhist
    1.41
     Buddhists
    1.41
     upaya
    1.22
     Buddhism
    1.20
     Buddha
    1.17
     Budd
    1.11
     Dharma
    1.08
     monks
    1.08
    Refuge
    0.99
     monastic
    0.99
    Activations Density 0.027%

    No Known Activations