© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57378
    Prev
    Next
    INDEX
    Explanations

    thymus, thymidine, thymocyte, Redmond, alfalfa

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

    references to the thymus organ in medical and scientific text.

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

    The neuron is highly sensitive to the character sequence “thym” (as found in words like thymus, thymic, thymocyte, thymidine, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    𐐪
    -2.66
    aphne
    -2.14
    鬭
    -2.13
     Answering
    -2.09
     Acknowled
    -2.09
    貽
    -2.08
    洐
    -2.06
    够了
    -2.03
     Dois
    -2.03
     discern
    -2.03
    POSITIVE LOGITS
    from
    2.83
    ar
    2.63
    which
    2.42
    耵
    2.42
    th
    2.39
     från
    2.34
     is
    2.33
    {
    2.27
    d
    2.17
     خاصی
    2.08
    Activations Density 0.013%

    No Known Activations