© 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. 105528
    Prev
    Next
    INDEX
    Explanations

    inflammatory mediators, cytokines, responses

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

    This neuron detects words related to inflammation and inflammatory processes in medical contexts.

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

    The neuron activates whenever the adjective “inflammatory” appears, i.e. it flags mentions of inflammation or inflammatory processes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    t
    -2.78
    .”
    -2.66
    Besides
    -2.55
    What
    -2.45
    Some
    -2.36
    er
    -2.36
    With
    -2.34
    Of
    -2.31
    ’
    -2.27
    Like
    -2.25
    POSITIVE LOGITS
    ),
    2.75
    鼷
    2.52
    茕
    2.48
    踅
    2.44
    
    2.42
    骉
    2.25
     is
    2.23
    艄
    2.20
    虯
    2.20
    días
    2.19
    Activations Density 0.011%

    No Known Activations