© 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. 119149
    Prev
    Next
    INDEX
    Explanations

    immune system regulation

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

    concepts related to the immune system, especially mentions of adaptive and innate immunity.

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

    The neuron strongly activates on immune-system and immunology terms (e.g. immunity, innate/adaptive immune, antimicrobial peptides, cytokines).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Whisper
    -0.81
    뇽
    -0.77
    entum
    -0.76
     atlik
    -0.74
     menonton
    -0.73
     VUL
    -0.73
     Whisper
    -0.72
    wanne
    -0.71
    zember
    -0.71
     Vorm
    -0.71
    POSITIVE LOGITS
     immune
    2.77
     immunity
    2.20
    immune
    1.97
     Immune
    1.88
     имму
    1.80
    immunity
    1.72
    免疫
    1.65
    Immune
    1.61
     adaptive
    1.55
     hum
    1.54
    Activations Density 0.255%

    No Known Activations