© 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. 84209
    Prev
    Next
    INDEX
    Explanations

    chemical formation and production

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

    chemical reactions and enzymatic processes in scientific contexts.

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

    The neuron fires on descriptions of biochemical or enzymatic reaction steps and associated chemical entities.

    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
     hilft
    -1.12
    łby
    -1.03
    fromString
    -1.02
     móg
    -1.02
     from
    -1.01
     dành
    -1.00
    niejsze
    -0.99
     dintr
    -0.99
     hjälper
    -0.97
     tiroirs
    -0.97
    POSITIVE LOGITS
     to
    3.88
     producing
    2.34
    producing
    2.09
     produce
    2.09
     forming
    2.00
    yielding
    1.96
     yielding
    1.95
     resulting
    1.81
    Producing
    1.80
     creating
    1.80
    Activations Density 0.259%

    No Known Activations