© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78184
    Prev
    Next
    INDEX
    Explanations

    Dr or Doctor followed by name

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

    The neuron is keyed to spotting occurrences of the “Dr.” honorific and the proper names around it.

    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
     journalists
    -1.04
     Journalist
    -0.88
     Neces
    -0.88
    neces
    -0.88
     contempl
    -0.87
     journalist
    -0.83
     journalistes
    -0.81
     journalism
    -0.79
    AXI
    -0.79
     journaliste
    -0.78
    POSITIVE LOGITS
     Dr
    2.80
    Dr
    2.45
     Doctor
    1.89
     dr
    1.72
     doctor
    1.63
    Doctor
    1.63
     Drs
    1.54
    doctor
    1.46
     доктор
    1.44
     DR
    1.41
    Activations Density 0.080%

    No Known Activations