© 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. 113052
    Prev
    Next
    INDEX
    Explanations

    sulfamethoxazole, Sulfadimethoxine, trimethoxyl

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

    The neuron activates for chemical compounds containing "ox" in their names, particularly pharmaceutical and chemical terms like "methoxazole" and "hydroxide".

    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
    i
    -2.42
    which
    -2.39
    有難
    -2.16
    ar
    -2.05
    …」
    -1.98
    ﮦ
    -1.97
     infierno
    -1.95
    主机
    -1.94
    from
    -1.92
    嘡
    -1.92
    POSITIVE LOGITS
     of
    2.66
    .
    2.36
     to
    2.22
    ൎ
    2.11
     you
    1.97
    姈
    1.97
    ikuti
    1.89
     has
    1.89
     explicación
    1.88
     и
    1.86
    Activations Density 0.004%

    No Known Activations