© 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. 34-GEMMASCOPE-RES-131K
    7. 2954
    Prev
    Next
    INDEX
    Explanations

    Interleukin-receptor relationships

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

    cytokine and interleukin receptor signaling molecules in scientific or medical text.

    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
    PREFACE
    -0.83
     Rollo
    -0.71
    ⓖ
    -0.69
     ornith
    -0.69
    islav
    -0.69
    scrollLeft
    -0.69
    ళ్
    -0.67
    ounty
    -0.67
     suiker
    -0.67
    FOREWORD
    -0.66
    POSITIVE LOGITS
     IL
    0.97
    STAT
    0.85
    Illinois
    0.84
     ILLINOIS
    0.83
     Illinois
    0.83
     cytokine
    0.82
     STAT
    0.82
    piration
    0.78
    shared
    0.77
    LENGTH
    0.75
    Activations Density 0.174%

    No Known Activations