© 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. 50298
    Prev
    Next
    INDEX
    Explanations

    phrases with specific subsequent terms

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

    The neuron responds to domain-specific technical terms and acronyms—especially capitalized keywords in patent and standards language.

    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
     evtl
    -1.05
     выходит
    -1.01
     دیدن
    -0.98
     видит
    -0.97
    ческом
    -0.91
    Ито
    -0.90
    
    -0.90
    椟
    -0.88
    完成です
    -0.88
     تحتاج
    -0.88
    POSITIVE LOGITS
     constantemente
    0.87
     Generally
    0.82
     Really
    0.82
     постоянно
    0.82
     Automatic
    0.82
     animosity
    0.81
     azúcar
    0.81
     aptly
    0.81
     на
    0.78
     Automated
    0.78
    Activations Density 0.925%

    No Known Activations