© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31141
    Prev
    Next
    INDEX
    Explanations

    business, CIS, purification, invention

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

    The neuron strongly activates on quoted field names and structural markers (e.g. “code”:, “templateKey”:, “searchCode”:) characteristic of JSON‐style key–value syntax.

    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
     administrator
    -0.96
     Administrator
    -0.93
     Admin
    -0.88
    ierte
    -0.86
    ्यू
    -0.84
     quart
    -0.84
     Kuk
    -0.84
    Vidi
    -0.84
     MySQL
    -0.83
    Kuk
    -0.81
    POSITIVE LOGITS
     cromado
    0.87
    对于
    0.86
    Business
    0.81
     Bisnis
    0.80
    据
    0.79
     rallado
    0.78
     Pact
    0.77
    nému
    0.77
    Interactive
    0.77
    年末
    0.77
    Activations Density 0.004%

    No Known Activations