© 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. 73710
    Prev
    Next
    INDEX
    Explanations

    global corporations

    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
     العمر
    -0.72
     انسان
    -0.72
    Демографія
    -0.70
    信仰
    -0.67
    lamide
    -0.66
    ünster
    -0.66
     Household
    -0.66
    grunns
    -0.65
    Caratteristiche
    -0.64
     consumer
    -0.64
    POSITIVE LOGITS
     corporate
    2.48
     Corporate
    2.06
    Corporate
    1.98
    corporate
    1.91
     corporation
    1.88
     tax
    1.72
     corporations
    1.57
     CORPOR
    1.48
     Corporation
    1.47
     корпора
    1.43
    Activations Density 0.016%

    No Known Activations