© 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. 32933
    Prev
    Next
    INDEX
    Explanations

    DWI courts

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

    The neuron flags mentions of DUI/DWI (driving under the influence) offenses.

    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
    墙壁
    -0.82
    VIRGO
    -0.81
    ApplicationTests
    -0.80
    ĸ
    -0.79
     diriger
    -0.79
    ărilor
    -0.79
     Rb
    -0.78
    chestra
    -0.77
    macbook
    -0.77
    ステン
    -0.76
    POSITIVE LOGITS
     ignition
    1.14
     court
    0.94
    conv
    0.93
     install
    0.93
    BAC
    0.89
     Installation
    0.87
     Driving
    0.87
     installing
    0.87
     Court
    0.85
    install
    0.84
    Activations Density 0.012%

    No Known Activations