© 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. 37738
    Prev
    Next
    INDEX
    Explanations

    nurse psychologist agent

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

    This neuron specifically detects the presence of the word “registered.”

    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
    ition
    -0.80
     rejoindre
    -0.75
    thon
    -0.72
    WAITING
    -0.71
    бу
    -0.71
    ука
    -0.71
     jouant
    -0.71
     expliquer
    -0.70
     obtenir
    -0.70
     chancellor
    -0.70
    POSITIVE LOGITS
     nurse
    1.02
     trademark
    1.01
    äfte
    1.00
     Registered
    0.98
    艸
    0.98
     architect
    0.95
     professional
    0.94
     registered
    0.93
     psychologist
    0.93
     nő
    0.93
    Activations Density 0.027%

    No Known Activations