© 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. 69577
    Prev
    Next
    INDEX
    Explanations

    Samantha or device

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

    The neuron strongly activates on occurrences of the proper name “Samantha.”

    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
     eccellente
    -3.14
     剧照
    -3.08
    櫺
    -3.03
    鬭
    -3.03
     丁目
    -2.97
     bellissimo
    -2.81
    螄
    -2.80
    鼱
    -2.80
    メリカ
    -2.78
    眥
    -2.77
    POSITIVE LOGITS
    ↵↵
    3.83
    :
    3.25
    -,
    2.94
    -
    2.84
    </h2>
    2.83
    ?
    2.73
          
    2.63
            
    2.58
    快要
    2.48
     той
    2.47
    Activations Density 0.002%

    No Known Activations