© 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. 31654
    Prev
    Next
    INDEX
    Explanations

    Buddhist or spiritual discourse

    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
    getRaw
    -0.86
     Wiggins
    -0.76
    ờ
    -0.75
    REEN
    -0.75
    Endor
    -0.74
    ℑ
    -0.73
    whelming
    -0.72
    ्रे
    -0.72
    stop
    -0.70
    hassee
    -0.70
    POSITIVE LOGITS
     chanting
    0.88
     Nhân
    0.88
     Nic
    0.81
     Toda
    0.81
     felicit
    0.78
     Goh
    0.78
    soka
    0.75
    ujud
    0.73
     practice
    0.71
    haviors
    0.70
    Activations Density 0.008%

    No Known Activations