© 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. 47857
    Prev
    Next
    INDEX
    Explanations

    John 3:16 pattern

    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
     medición
    -0.80
     temiz
    -0.80
    hyung
    -0.78
    lysses
    -0.77
     Luke
    -0.77
    owały
    -0.77
    잡
    -0.76
    paedia
    -0.75
    ujące
    -0.75
     classificação
    -0.75
    POSITIVE LOGITS
     John
    2.19
    John
    1.89
     john
    1.52
    john
    1.47
    JOHN
    1.45
     JOHN
    1.41
     Джон
    1.35
     Joh
    1.33
    Joh
    1.18
    ジョン
    1.10
    Activations Density 0.018%

    No Known Activations