© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73473
    Prev
    Next
    INDEX
    Explanations

    DUI drunk driving

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

    The neuron detects mentions of DUI/DWI or driving‐under‐the‐influence contexts (drunk‐driving 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_10/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
    fatalError
    -1.70
    </h5>
    -1.66
    ↵↵↵↵↵↵↵
    -1.55
    </em>
    -1.52
    casa
    -1.45
    ]
    -1.44
     tener
    -1.43
    }});
    -1.41
    ↵↵↵↵↵↵↵↵↵↵↵
    -1.40
    ].
    -1.40
    POSITIVE LOGITS
    Ᏹ
    1.40
     zari
    1.35
     then
    1.35
    魨
    1.34
    カ
    1.34
    喏
    1.34
     píše
    1.33
    ПРО
    1.30
    髎
    1.30
     săptăm
    1.28
    Activations Density 0.014%

    No Known Activations