© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6837
    Prev
    Next
    INDEX
    Explanations

    lipase, esterase, hydrolase

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

    words related to enzymes, particularly lipases and proteases, in scientific contexts.

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

    This neuron is primarily sensitive to biochemical terms bearing the “-ase” (and related “ester”) endings, as found in enzyme names and ester-containing compounds.

    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
     ENTITY
    -0.81
     intruders
    -0.69
     左
    -0.69
    kening
    -0.67
     Nieren
    -0.66
     Vea
    -0.66
     barrio
    -0.66
    extract
    -0.65
    questions
    -0.64
     Mina
    -0.64
    POSITIVE LOGITS
     hydro
    1.71
     hydrolysis
    1.66
     Hydro
    1.47
    Hydro
    1.42
     hydroly
    1.39
     lip
    1.34
    hydro
    1.20
     digestive
    1.01
     hidro
    0.99
     pancreatic
    0.98
    Activations Density 0.190%

    No Known Activations