© 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. 129089
    Prev
    Next
    INDEX
    Explanations

    immunoglobulin chains and receptors

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

    terms related to immunology, particularly T-cell receptors, immunoglobulins, and molecular biology of the immune system.

    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
    ut
    -1.29
    емся
    -1.24
     stöd
    -1.23
    wór
    -1.11
     instead
    -1.11
     mariposa
    -1.09
     augusti
    -1.09
     quand
    -1.06
     aldrig
    -1.04
     kinases
    -1.04
    POSITIVE LOGITS
     his
    1.56
     coscienza
    1.37
     that
    1.29
    scalatest
    1.29
    carian
    1.16
    ampaikan
    1.16
     esigen
    1.14
    bbons
    1.13
    続きを読む
    1.13
    昨天
    1.13
    Activations Density 0.232%

    No Known Activations