© 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. 116596
    Prev
    Next
    INDEX
    Explanations

    json loads and dumps

    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
     joys
    -0.88
    Reminders
    -0.75
     vb
    -0.75
     boto
    -0.75
     GetAll
    -0.75
    gger
    -0.73
     Emile
    -0.71
    Invoices
    -0.71
     Lég
    -0.71
    Emile
    -0.71
    POSITIVE LOGITS
    loads
    1.66
     loads
    1.63
     Loads
    1.16
    Loads
    1.16
     dumps
    1.12
    dumps
    1.06
    load
    1.00
     load
    0.94
     cargas
    0.85
     transmitter
    0.84
    Activations Density 0.007%

    No Known Activations