© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99512
    Prev
    Next
    INDEX
    Explanations

    first name Joe

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

    This neuron detects occurrences of the proper name “Joe.”

    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
    都好
    -0.90
     own
    -0.87
     rele
    -0.86
     headlong
    -0.85
    Lovely
    -0.85
     такие
    -0.84
    t
    -0.84
    間に
    -0.84
     този
    -0.84
     default
    -0.84
    POSITIVE LOGITS
     joe
    1.41
     Biden
    1.39
    Joe
    1.32
    Biden
    1.30
     Joe
    1.27
    joe
    1.20
     JOE
    1.20
     Rogan
    1.10
    JOE
    1.06
     Stalin
    1.05
    Activations Density 0.009%

    No Known Activations