© 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. 34-GEMMASCOPE-RES-131K
    7. 116033
    Prev
    Next
    INDEX
    Explanations

    eosinophil

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

    This neuron detects terms related to eosinophils, white blood cells involved in allergic and inflammatory responses.

    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_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
     Integr
    -0.77
     pousser
    -0.75
    UEFA
    -0.75
    ﻭ
    -0.74
     employes
    -0.72
    ndice
    -0.72
    rücke
    -0.71
    柔らか
    -0.71
     aliases
    -0.70
    scaler
    -0.70
    POSITIVE LOGITS
     eosin
    1.16
     bas
    1.11
     Bas
    0.94
    Bas
    0.86
     electron
    0.83
     E
    0.82
    bas
    0.82
     acid
    0.81
    Gran
    0.81
     Gran
    0.81
    Activations Density 0.096%

    No Known Activations