© 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. 10-GEMMASCOPE-RES-131K
    7. 44697
    Prev
    Next
    INDEX
    Explanations

    infectious disease

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

    This neuron identifies the word "infectious" when it appears before "disease(s)" or "agents," particularly in medical and scientific 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
    Ⲉ
    -2.67
    塍
    -2.42
    ﮩ
    -2.42
     красивые
    -2.38
    ができ
    -2.34
    amir
    -2.28
    饪
    -2.22
    髪の
    -2.19
     samlet
    -2.19
    ágenes
    -2.17
    POSITIVE LOGITS
    轳
    3.27
     Then
    2.91
     desolate
    2.77
    ࿚
    2.70
     wayward
    2.56
    انگلیسی
    2.52
    
    2.45
     große
    2.42
    中心的
    2.41
    Schicken
    2.33
    Activations Density 0.013%

    No Known Activations