© 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. 64177
    Prev
    Next
    INDEX
    Explanations

    Kanye West, Catherine the Great

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

    This neuron is triggered by biographical or profile information—especially personal names, birth details, dates, and quoted descriptors of a person.

    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
     frightening
    -0.87
     staggering
    -0.75
     =~
    -0.72
    ۞
    -0.72
     Hein
    -0.72
    ltk
    -0.71
     extraordinarily
    -0.71
     neatly
    -0.71
     postage
    -0.69
     FAQs
    -0.69
    POSITIVE LOGITS
     KAN
    1.06
     Chicago
    1.03
     Yee
    1.02
     Kanye
    1.01
    KAN
    1.00
    Samp
    0.94
    samp
    0.93
    ⛷
    0.93
    Chicago
    0.90
    plaintext
    0.85
    Activations Density 0.017%

    No Known Activations