© 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. 109564
    Prev
    Next
    INDEX
    Explanations

    Saint's Church, School, College

    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
    Asign
    -0.82
    鄂
    -0.78
     stär
    -0.74
    割と
    -0.74
    main
    -0.73
     hörte
    -0.73
     vuole
    -0.72
     lekker
    -0.71
     problémy
    -0.69
    Introduce
    -0.69
    POSITIVE LOGITS
     Church
    1.17
     church
    1.13
     College
    1.12
     school
    1.08
     college
    0.99
    College
    0.93
     organ
    0.91
    Church
    0.88
     School
    0.87
     hospital
    0.82
    Activations Density 0.021%

    No Known Activations