© 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. 10-GEMMASCOPE-RES-131K
    7. 48491
    Prev
    Next
    INDEX
    Explanations

    combating diseases and threats

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

    phrases related to fighting against or combating something, particularly in contexts of terrorism, disease, or other threats.

    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_10/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
     for
    -1.73
    以上です
    -1.70
    鳧
    -1.58
    我会
    -1.55
     unruly
    -1.50
    اسية
    -1.46
    Demografie
    -1.46
     testimonio
    -1.45
    我来
    -1.45
     more
    -1.43
    POSITIVE LOGITS
    >();
    1.64
     található
    1.53
    他的
    1.48
     toujours
    1.46
     '\
    1.45
    ;
    1.43
    那些
    1.42
    LANTA
    1.41
    atonin
    1.41
    iac
    1.40
    Activations Density 0.032%

    No Known Activations