© 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. 109489
    Prev
    Next
    INDEX
    Explanations

    sulfur, iron, zinc, cluster, proteins

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

    This neuron detects biochemical and molecular biology terminology, particularly related to enzymes, proteins, and chemical compounds.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     resized
    -0.72
     kelp
    -0.69
     nâu
    -0.68
     Palestinians
    -0.67
     phosphate
    -0.66
     jeep
    -0.66
     age
    -0.65
     psoriasis
    -0.65
    BaseAdapter
    -0.65
     H
    -0.63
    POSITIVE LOGITS
     cluster
    1.02
     proteínas
    1.02
    cluster
    0.94
     clusters
    0.94
     acon
    0.93
    zinc
    0.89
     Cluster
    0.83
     iron
    0.82
    Cluster
    0.82
     irons
    0.81
    Activations Density 0.125%

    No Known Activations