© 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. 10-GEMMASCOPE-RES-131K
    7. 99645
    Prev
    Next
    INDEX
    Explanations

    sympathy and synonyms

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

    The neuron activates on words and word stems expressing sympathy or empathy (e.g. “sympathy,” “sympathized”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words formed with the syn-/sym- prefix and their derivatives.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "sympathy" or variations of "synonym" in technical or scientific contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    諴
    -2.77
    ！"
    -2.77
     are
    -2.70
    啣
    -2.69
    轳
    -2.50
    豨
    -2.48
    餿
    -2.47
    魨
    -2.45
    躡
    -2.42
    猡
    -2.39
    POSITIVE LOGITS
    .
    3.50
    ↵↵
    3.13
    2.78
    a
    2.72
    ?
    2.27
    别人
    2.20
    ;
    2.17
    ’
    2.09
    ,”
    2.08
    熜
    2.06
    Activations Density 0.001%
    No Known Activations