© 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. 11767
    Prev
    Next
    INDEX
    Explanations

    government agencies and authorities

    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
     antioxidants
    -0.83
    aptors
    -0.78
     Königin
    -0.76
    méno
    -0.75
    UMN
    -0.75
     tulle
    -0.74
    RequiresApi
    -0.73
    kingen
    -0.73
    Right
    -0.73
     ASSOCI
    -0.72
    POSITIVE LOGITS
     agency
    1.89
     Agency
    1.62
    Agency
    1.54
    agency
    1.36
     regulator
    1.33
     Authority
    1.30
     AGENCY
    1.29
     authority
    1.24
     agencia
    1.23
     agencies
    1.21
    Activations Density 0.054%

    No Known Activations