© 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. 102658
    Prev
    Next
    INDEX
    Explanations

    prostaglandin and its derivatives

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

    biochemical terms related to prostaglandins and their metabolites in medical research.

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

    The neuron is specialized for detecting mentions of prostaglandin‐type molecules (e.g. PGI₂, PGE₂, prostacyclin) and related biochemical 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
    oude
    -0.71
     soldier
    -0.71
     militares
    -0.68
    胍
    -0.68
     Simona
    -0.66
    ajevo
    -0.66
     soldiers
    -0.66
    ੰ
    -0.66
     vardır
    -0.65
     predicates
    -0.65
    POSITIVE LOGITS
     prostagland
    1.84
     prost
    1.38
     Prost
    1.23
    prost
    1.22
    PG
    1.14
     PG
    1.09
    stagland
    1.06
    PGA
    0.85
     Pg
    0.85
     PGA
    0.82
    Activations Density 0.209%

    No Known Activations