© 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. 34-GEMMASCOPE-RES-131K
    7. 4110
    Prev
    Next
    INDEX
    Explanations

    name, names, nombre, 名, باسم

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

    The neuron detects occurrences of the phrase “in the name of.”

    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
    انگلیسی
    -0.83
     定制
    -0.81
     字母
    -0.76
    댁
    -0.75
     hẳn
    -0.75
    と話
    -0.72
    Sila
    -0.72
    ंदु
    -0.70
     尺寸
    -0.70
     Beschwerden
    -0.69
    POSITIVE LOGITS
     name
    4.03
    name
    2.88
     Name
    2.84
     باسم
    2.63
    的名
    2.56
    名
    2.55
    Name
    2.55
     names
    2.33
     NAME
    2.28
     nombre
    2.19
    Activations Density 0.046%

    No Known Activations