© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32152
    Prev
    Next
    INDEX
    Explanations

    pastor and church

    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
     Cyclic
    -0.75
    aussian
    -0.74
    两者
    -0.71
     Consult
    -0.70
     contested
    -0.69
     recruited
    -0.68
    进来
    -0.68
     سواری
    -0.67
    Peugeot
    -0.66
     Geden
    -0.66
    POSITIVE LOGITS
     church
    1.96
    Pastor
    1.90
     Pastor
    1.73
     pastor
    1.67
     pastors
    1.59
    pastor
    1.53
    Church
    1.46
     Church
    1.45
    church
    1.40
     CHURCH
    1.25
    Activations Density 0.035%

    No Known Activations