© 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. 21126
    Prev
    Next
    INDEX
    Explanations

    immune cells and processes

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

    This neuron recognizes scientific content related to immunology, particularly focusing on T cells, cellular immune responses, and biological mechanisms in immune system function.

    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
     теперь
    -1.44
     ſec
    -1.36
     ſu
    -1.31
    辍
    -1.29
     aſ
    -1.28
     phare
    -1.27
     suave
    -1.26
     Algunos
    -1.24
     Eſ
    -1.24
     eſt
    -1.23
    POSITIVE LOGITS
     great
    1.63
    ynchronously
    1.42
     good
    1.41
    Both
    1.41
     sufficient
    1.39
     both
    1.38
     outstanding
    1.37
     first
    1.36
     out
    1.36
     lengthy
    1.32
    Activations Density 1.001%

    No Known Activations