© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101163
    Prev
    Next
    INDEX
    Explanations

    coronal, coronary, Corona Virus

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

    The neuron identifies variations of the word "corona" (including "coronal," "coronary," "coronavirus") across different contexts.

    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
    訁
    -3.06
    真的是
    -2.66
    "}}>
    -2.47
    ឣ
    -2.45
    祘
    -2.45
    茑
    -2.44
     {
    -2.42
    ()<<
    -2.42
    してました
    -2.41
    柠
    -2.34
    POSITIVE LOGITS
    ↵
    3.86
     {
    2.45
     ilumina
    2.27
    咂
    2.25
     outras
    2.17
     altre
    2.17
     acepción
    2.14
     commensurate
    2.05
     Incredible
    2.03
    心头
    2.03
    Activations Density 0.001%

    No Known Activations