© 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. 90582
    Prev
    Next
    INDEX
    Explanations

    commissions, elections, and employment

    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
    剱
    -0.77
     مدیر
    -0.73
    െയ
    -0.72
     ADVANCE
    -0.72
     minne
    -0.71
    長男
    -0.71
     xuyên
    -0.70
    MMM
    -0.70
     PROGRAM
    -0.69
     צו
    -0.69
    POSITIVE LOGITS
     commission
    3.20
     Commission
    3.05
     commissions
    2.81
    Commission
    2.66
    commission
    2.61
     COMMISSION
    2.31
     Commissions
    2.27
     commissioners
    2.11
     Comisión
    1.87
     commissioner
    1.71
    Activations Density 0.098%

    No Known Activations