© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57651
    Prev
    Next
    INDEX
    Explanations

    names starting with Joanna or Kr

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

    The neuron fires on occurrences of the proper name “Joanna.”

    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
    u
    -3.06
    ו
    -2.91
    y
    -2.75
    ?”
    -2.72
     alcuni
    -2.69
    那种
    -2.66
     brazen
    -2.64
     exitos
    -2.53
     efectivamente
    -2.45
    
    -2.44
    POSITIVE LOGITS
    0
    2.72
    轫
    2.38
    دين
    2.08
    ﺲ
    2.08
    چک
    2.06
     蓋
    2.05
    جوا
    2.00
     需要
    1.99
     兩
    1.98
     britann
    1.97
    Activations Density 0.002%

    No Known Activations