© 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. 63075
    Prev
    Next
    INDEX
    Explanations

    China and Covid-related news

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

    mentions of China in news and article headlines.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is a detector for references to China or Chinese‐related contexts in news headlines and articles.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ե
    -0.76
     userEmail
    -0.75
    נפ
    -0.73
     niggas
    -0.73
    ꜣ
    -0.71
    opedia
    -0.70
    Imgur
    -0.69
     جمه
    -0.69
    colormap
    -0.69
    icture
    -0.68
    POSITIVE LOGITS
     Covid
    1.45
     covid
    1.38
     zero
    1.35
     Omicron
    1.34
     Zero
    1.29
    zero
    1.27
     lockdowns
    1.22
     COVID
    1.19
    Zero
    1.14
     PCR
    1.13
    Activations Density 0.005%

    No Known Activations