© 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. 39797
    Prev
    Next
    INDEX
    Explanations

    eosinophilia

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

    This neuron detects mentions of "eosin" and related terms in biological/medical 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
    
    -3.14
    伫
    -2.70
    zló
    -2.56
    는
    -2.56
    $,
    -2.55
    浔
    -2.47
    gées
    -2.42
     zweiten
    -2.38
    もありますが
    -2.38
    Werdegang
    -2.36
    POSITIVE LOGITS
    {
    2.70
    </strong>
    2.28
    _
    2.14
    钇
    2.11
    ↵
    2.08
    鏨
    2.08
    または
    2.06
     problemów
    1.98
    緇
    1.95
    “
    1.89
    Activations Density 0.006%

    No Known Activations