© 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. 2077
    Prev
    Next
    INDEX
    Explanations

    the gospel

    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
    permitted
    -0.77
    XAxis
    -0.76
     pipes
    -0.75
    ovala
    -0.72
     Pollack
    -0.71
     Isabella
    -0.70
    όν
    -0.70
    tray
    -0.69
    griff
    -0.68
     Clemente
    -0.68
    POSITIVE LOGITS
     gospel
    5.16
     Gospel
    4.91
    Gospel
    3.80
    福音
    2.59
    ospel
    2.59
     Gospels
    2.41
     Evangelio
    2.02
    ospels
    1.92
     evangé
    1.77
     evange
    1.73
    Activations Density 0.027%

    No Known Activations