© 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. 30133
    Prev
    Next
    INDEX
    Explanations

    medical emergency

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

    medical or emergency situations and related terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    anges
    -0.80
    keln
    -0.79
     الذات
    -0.78
    unsch
    -0.77
    rite
    -0.76
    小心翼翼
    -0.75
    蔺
    -0.75
    Plz
    -0.74
    сія
    -0.73
     Mbps
    -0.72
    POSITIVE LOGITS
     emergency
    6.41
     emergencies
    5.25
    emergency
    5.19
     Emergency
    4.59
    Emergency
    4.53
     EMERGENCY
    4.03
    EMERGENCY
    3.66
     emergencia
    3.64
    緊急
    3.42
    紧急
    3.19
    Activations Density 0.064%

    No Known Activations