© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34694
    Prev
    Next
    INDEX
    Explanations

    reported deaths and casualties

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

    numerical reporting of fatalities in news stories about disasters, attacks, and incidents.

    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
    பெ
    -0.87
     pandemic
    -0.84
     problema
    -0.81
    很大的
    -0.78
    arza
    -0.77
     Thieves
    -0.77
    return
    -0.76
    áculo
    -0.75
     lutego
    -0.75
     Pandemic
    -0.74
    POSITIVE LOGITS
     confirmed
    1.48
     fatalities
    1.47
     death
    1.45
     deaths
    1.38
     toll
    1.33
    confirmed
    1.23
    Bodies
    1.20
     confirmación
    1.19
     подтвер
    1.19
     bodies
    1.19
    Activations Density 0.038%

    No Known Activations