© 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. 110710
    Prev
    Next
    INDEX
    Explanations

    Jesus teaching and healing

    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
     menyen
    -0.83
    Faith
    -0.81
    情報
    -0.80
     demokra
    -0.80
     สวย
    -0.79
    faith
    -0.79
     cosp
    -0.79
    hig
    -0.78
    信仰
    -0.77
    PSG
    -0.77
    POSITIVE LOGITS
     teaching
    1.55
     teach
    1.29
     himself
    1.16
     Himself
    1.12
     Teaching
    1.12
     Teach
    1.11
     healing
    1.08
    teaching
    1.08
    Teach
    1.07
    Teaching
    1.06
    Activations Density 0.015%

    No Known Activations