© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73502
    Prev
    Next
    INDEX
    Explanations

    aching, ailments, heartaches

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

    words related to pain, particularly "ache," "aching," and "aches."

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

    The neuron fires on various forms of “ache” (ache, aches, aching, achiness), i.e. words indicating bodily pain or discomfort.

    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
    真的很
    -2.33
    噥
    -2.25
    鱻
    -2.19
    啰
    -2.17
    にほんブログ村
    -2.14
    ༐
    -2.14
     會
    -2.13
     場所
    -2.11
    に於
    -2.11
    However
    -2.09
    POSITIVE LOGITS
    geſ
    2.42
     pudieron
    2.20
    mathrm
    2.20
    ↵↵
    2.17
    ↵
    2.17
     siapa
    2.16
    '
    2.00
    ',
    1.98
    或是
    1.95
     sobretudo
    1.94
    Activations Density 0.004%

    No Known Activations