© 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. 65873
    Prev
    Next
    INDEX
    Explanations

    json marshal or decoder

    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
    ※
    -0.84
     cerimonia
    -0.84
     Nervous
    -0.78
    COL
    -0.77
     Paraná
    -0.77
    fmt
    -0.76
    itiert
    -0.75
    악
    -0.75
    理念
    -0.75
    フィン
    -0.75
    POSITIVE LOGITS
     body
    0.99
     JSON
    0.92
    Indent
    0.91
    decoder
    0.90
     json
    0.90
     Marshall
    0.85
     decoder
    0.84
     Marshal
    0.82
    лега
    0.79
     jsonData
    0.78
    Activations Density 0.039%

    No Known Activations