© 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. 99726
    Prev
    Next
    INDEX
    Explanations

    Blac Chyna and celebrity names

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

    The neuron is most strongly activated by capitalized named entities (especially celebrity/person names).

    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
     intimidation
    -0.82
    崙
    -0.79
    clientWidth
    -0.79
    植
    -0.78
    太子
    -0.77
    undam
    -0.73
    Sera
    -0.71
    Viited
    -0.71
     sketches
    -0.71
    Maja
    -0.70
    POSITIVE LOGITS
     Kylie
    1.34
     Jenner
    1.23
    Kylie
    1.00
     Storm
    0.93
    カイ
    0.88
    comma
    0.83
    ्रो
    0.81
    atii
    0.81
     Ky
    0.79
    storm
    0.79
    Activations Density 0.006%

    No Known Activations