© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29934
    Prev
    Next
    INDEX
    Explanations

    tragic accidents or sudden events

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

    The neuron detects mentions of serious physical injuries or traumatic accidents.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     WALT
    -0.74
     holog
    -0.73
    izumi
    -0.71
     apologizing
    -0.71
    icina
    -0.71
     kematian
    -0.70
     litio
    -0.69
    ścić
    -0.69
     Deceased
    -0.69
    ppuden
    -0.68
    POSITIVE LOGITS
     accident
    2.38
     accidents
    1.92
     motorcycle
    1.60
     accidente
    1.48
     acidente
    1.46
     Accident
    1.45
     skiing
    1.39
     accidental
    1.38
     accidentes
    1.38
    accident
    1.34
    Activations Density 0.086%

    No Known Activations