© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78347
    Prev
    Next
    INDEX
    Explanations

    industries and sectors

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

    The neuron fires on tokens naming industry sectors (often in a comma-and list), such as “Technology,” “Media,” “Tele­communications,” “Transport,” and “Retail.”

    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
    empresas
    -0.89
     отметил
    -0.86
    resultat
    -0.85
    белый
    -0.82
    zapatos
    -0.82
    ydı
    -0.81
     náv
    -0.81
    oubtedly
    -0.80
     menciona
    -0.80
     заявил
    -0.79
    POSITIVE LOGITS
     healthcare
    1.62
     hospitality
    1.56
     manufacturing
    1.53
     retail
    1.45
     education
    1.43
     health
    1.27
     finance
    1.25
     government
    1.24
     energy
    1.20
     Education
    1.20
    Activations Density 0.052%

    No Known Activations