© 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. 57677
    Prev
    Next
    INDEX
    Explanations

    fatal or lethal outcomes

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

    diseases and medical conditions described as potentially fatal or life-threatening.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Grazie
    -0.80
    Pager
    -0.79
    Цель
    -0.78
    受伤
    -0.78
     мәкал
    -0.77
    lığ
    -0.77
    挞
    -0.77
    Další
    -0.74
    getService
    -0.74
     Cellar
    -0.74
    POSITIVE LOGITS
     fatal
    5.00
    fatal
    4.03
     lethal
    3.75
     deadly
    3.70
     Fatal
    3.52
    Fatal
    3.31
     fatally
    3.06
    lethal
    3.03
    致命
    2.83
     Deadly
    2.75
    Activations Density 0.182%

    No Known Activations