© 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. 75865
    Prev
    Next
    INDEX
    Explanations

    state-owned corporations and companies

    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
    өздер
    -0.86
    olah
    -0.83
    GTCX
    -0.81
     phong
    -0.79
     Duque
    -0.79
    тропо
    -0.78
    unger
    -0.77
    NGO
    -0.76
     Banking
    -0.75
     klub
    -0.75
    POSITIVE LOGITS
     state
    1.14
     estatal
    0.96
     corporation
    0.96
     company
    0.89
     Corporation
    0.87
    Empresa
    0.85
     państw
    0.84
     estatales
    0.83
     JSC
    0.82
     national
    0.82
    Activations Density 0.026%

    No Known Activations