© 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. 48618
    Prev
    Next
    INDEX
    Explanations

    vehicle accidents and collisions

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

    This neuron detects descriptions of people being struck by or injured in vehicle “hit-and-run” or run-over incidents.

    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
    Prevent
    -0.89
     combate
    -0.88
    riften
    -0.81
    prevent
    -0.78
     Prevent
    -0.76
    IRM
    -0.76
    trong
    -0.73
    चार
    -0.71
     impuestos
    -0.71
    Smoking
    -0.71
    POSITIVE LOGITS
     hit
    2.98
    hit
    2.44
     Hit
    2.34
    Hit
    2.33
     HIT
    1.84
    HIT
    1.74
     hits
    1.67
     collisions
    1.52
     collision
    1.48
     hitting
    1.45
    Activations Density 0.022%

    No Known Activations