© 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. 91198
    Prev
    Next
    INDEX
    Explanations

    Gson parsing library

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects references to the Java Gson library (e.g. import or use of Gson and related types).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    лежа
    -0.85
     granja
    -0.83
     shipyard
    -0.82
     muziek
    -0.81
    jecture
    -0.80
     outlay
    -0.79
    ulante
    -0.75
    囑
    -0.75
     login
    -0.75
     gradualmente
    -0.75
    POSITIVE LOGITS
     päivä
    0.82
     智
    0.80
     kartą
    0.79
     perguntou
    0.76
     geogra
    0.75
     conhece
    0.74
     noblesse
    0.73
    їн
    0.73
     California
    0.72
    Terminal
    0.71
    Activations Density 0.004%

    No Known Activations