© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109273
    Prev
    Next
    INDEX
    Explanations

    NC followed by codes or types

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

    The neuron detects mentions of formal institution names—especially “National Center for …” phrases and their related acronyms.

    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
     промышленности
    -0.78
    tida
    -0.72
     prazo
    -0.71
     Lycée
    -0.69
    ారి
    -0.67
     Ceb
    -0.67
     onslaught
    -0.66
     Entra
    -0.66
    챕
    -0.65
    र्च
    -0.65
    POSITIVE LOGITS
     NC
    1.34
    NC
    0.98
     NCT
    0.96
    nc
    0.96
     nc
    0.90
     Nc
    0.88
    NCT
    0.84
    Outline
    0.82
     NCR
    0.82
     NCC
    0.81
    Activations Density 0.035%

    No Known Activations