© 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. 102501
    Prev
    Next
    INDEX
    Explanations

    organizations or businesses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     человека
    -1.19
     humans
    -1.01
    人员
    -1.00
    人們
    -1.00
     людини
    -0.98
     человек
    -0.96
    คน
    -0.96
     PEOPLE
    -0.92
     Personnel
    -0.89
     Individuals
    -0.88
    POSITIVE LOGITS
     their
    1.84
     organizations
    1.83
     groups
    1.69
     institutions
    1.66
     organisations
    1.61
     businesses
    1.59
     places
    1.37
     companies
    1.34
     animals
    1.34
     nations
    1.28
    Activations Density 0.075%

    No Known Activations