© 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. 10-GEMMASCOPE-RES-131K
    7. 20073
    Prev
    Next
    INDEX
    Explanations

    evangelical faith and Christian concepts

    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_10/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
    which
    -1.95
     that
    -1.95
     to
    -1.86
     by
    -1.82
     which
    -1.70
     reinforce
    -1.70
     That
    -1.67
    あるいは
    -1.66
     be
    -1.66
     solidify
    -1.61
    POSITIVE LOGITS
     zin
    1.59
     فلسط
    1.55
     gewi
    1.54
     evangelical
    1.52
    骝
    1.52
    icône
    1.51
    部分
    1.49
     pioneers
    1.48
     Dinas
    1.46
    RODUCTION
    1.45
    Activations Density 0.007%

    No Known Activations