© 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. 34778
    Prev
    Next
    INDEX
    Explanations

    anti- inflammatory and cholesterol inhibition

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

    scientific terminology related to biochemical and pharmacological activities, especially anti-inflammatory and antioxidant properties in research studies.

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

    The neuron reliably fires on phrases describing scientific bioactivity assays and compound property evaluations (e.g. “in vitro,” “antioxidant,” “antibacterial,” “anti-proliferative,” etc.).

    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
    Legături
    -0.82
    uebe
    -0.81
     Kör
    -0.76
    ptor
    -0.75
     satur
    -0.75
     biology
    -0.74
     forceps
    -0.74
    诲
    -0.73
    digd
    -0.73
    ługi
    -0.73
    POSITIVE LOGITS
     valamint
    0.79
    альные
    0.77
     WRITE
    0.77
     konkrét
    0.77
     Pří
    0.76
     méret
    0.76
    COX
    0.73
    超市
    0.73
    UserModel
    0.72
    现代
    0.72
    Activations Density 0.171%

    No Known Activations