© 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. 22-GEMMASCOPE-RES-131K
    7. 73601
    Prev
    Next
    INDEX
    Explanations

    key-value pairs, structural elements

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

    The neuron fires on identifier names—especially snake_case or quoted field/key names in code or structured data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    lifford
    -0.99
    
    -0.98
    falgar
    -0.94
    maining
    -0.94
    positorio
    -0.92
     estratégico
    -0.90
    jason
    -0.90
    小山
    -0.90
    ValueGenerated
    -0.89
    harmonie
    -0.89
    POSITIVE LOGITS
     height
    1.10
     length
    1.05
     width
    0.98
     variables
    0.91
    錯誤
    0.89
    漫畫
    0.88
     brukar
    0.88
     location
    0.87
    的数量
    0.85
    antidad
    0.84
    Activations Density 0.080%

    No Known Activations