© 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. 82867
    Prev
    Next
    INDEX
    Explanations

    supplements and chemical compounds

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

    chemical compounds and substances used in laboratory culture media.

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

    The neuron strongly activates on chemical reagent and measurement tokens—i.e. parts of compound names (with hyphens, letters, and numbers) and numeric or unit-specifying tokens.

    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
    रे
    -0.82
     impresora
    -0.81
    égio
    -0.81
     histograms
    -0.81
    نه
    -0.79
     tâche
    -0.78
    CYAN
    -0.78
     задний
    -0.77
    sockfd
    -0.77
    cyan
    -0.77
    POSITIVE LOGITS
     vitamins
    0.94
    additional
    0.93
     Vitamins
    0.81
     additional
    0.81
    trace
    0.79
     trace
    0.79
    ADDITIONAL
    0.79
     supplementary
    0.77
     supplementation
    0.77
     supplement
    0.77
    Activations Density 0.024%

    No Known Activations