© 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. 34-GEMMASCOPE-RES-131K
    7. 12285
    Prev
    Next
    INDEX
    Explanations

    medicinal compounds and substances

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

    scientific and medical terminology, especially plant-derived substances and compounds.

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

    the neuron activates on technical domain–specific terms, especially chemical and botanical names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    诱
    -0.74
     Optimum
    -0.73
    ði
    -0.73
    搾
    -0.72
    subsubsection
    -0.72
     ushort
    -0.71
    ferencia
    -0.71
     kirja
    -0.70
    ઠ
    -0.70
    Dayton
    -0.69
    POSITIVE LOGITS
     fluide
    0.96
    camp
    0.90
     Lancet
    0.89
     subli
    0.87
     administered
    0.86
     compounded
    0.85
     offic
    0.85
     cam
    0.82
     precipitated
    0.82
     preparations
    0.82
    Activations Density 0.020%

    No Known Activations