© 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. 22-GEMMASCOPE-RES-131K
    7. 128960
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on parenthetical birth or maiden names introduced by “née.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    surnames in biographies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    usas
    -0.87
     Bankruptcy
    -0.87
     TabLayout
    -0.87
     Negotiations
    -0.86
    СЕ
    -0.86
    jęcia
    -0.86
     austerity
    -0.84
    PDE
    -0.82
    惊艳
    -0.82
     diamètre
    -0.81
    POSITIVE LOGITS
     then
    0.99
    ﴿
    0.98
     after
    0.90
    tyl
    0.90
     dilakukan
    0.87
    uertos
    0.87
    voll
    0.86
     her
    0.86
     take
    0.85
    chement
    0.84
    Activations Density 0.007%

    No Known Activations