© 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. 82611
    Prev
    Next
    INDEX
    Explanations

    phagocytic activity and engulfment

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

    terminology related to immune system processes, particularly phagocytosis and macrophage activity.

    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
    glGet
    -0.79
    alei
    -0.75
     Autoren
    -0.71
    ὕ
    -0.70
    umbag
    -0.70
    getLayout
    -0.69
    letal
    -0.69
     apel
    -0.68
    benchmark
    -0.67
    gregor
    -0.66
    POSITIVE LOGITS
     phag
    1.60
     engulf
    1.36
     ingest
    1.09
    pha
    1.02
     ingestion
    1.01
     engulfed
    1.00
    吞噬
    0.98
     killing
    0.94
     chemo
    0.93
     clearance
    0.88
    Activations Density 0.155%

    No Known Activations