© 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. 117540
    Prev
    Next
    INDEX
    Explanations

    accidents and crashes

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

    The main thing this neuron does is detect mentions of vehicle crashes, traffic accidents, and related injury events.

    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
    atischen
    -0.80
    挑戰
    -0.79
    AZIONI
    -0.77
     therapies
    -0.75
    应对
    -0.74
     surfaces
    -0.73
    webp
    -0.73
    錮
    -0.72
     durations
    -0.72
    Challenges
    -0.72
    POSITIVE LOGITS
     accidents
    3.70
     accident
    3.59
     crash
    2.92
     crashes
    2.77
     Accidents
    2.56
    accident
    2.30
    事故
    2.27
     accidentes
    2.23
    crash
    2.23
     Accident
    2.16
    Activations Density 0.061%

    No Known Activations