© 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. 10-GEMMASCOPE-RES-131K
    7. 112232
    Prev
    Next
    INDEX
    Explanations

    Nicki Minaj and Q: questions

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

    The neuron is keyed to mentions of the artist “Nicki Minaj.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     from
    -2.91
     multitude
    -2.47
    ”,
    -2.41
     oppressive
    -2.39
     simplistic
    -2.31
     plethora
    -2.28
     exquisite
    -2.27
     This
    -2.23
     Geschä
    -2.22
    ↑↑↑</
    -2.20
    POSITIVE LOGITS
    鵙
    2.84
    踯
    2.50
    蚡
    2.48
    
    2.44
    糴
    2.41
    茈
    2.33
    埽
    2.28
    
    2.27
    隳
    2.23
     reiter
    2.22
    Activations Density 0.002%

    No Known Activations