© 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. 6790
    Prev
    Next
    INDEX
    Explanations

    Federal, federated, or Fédération

    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
     secciones
    -0.96
     cerrados
    -0.89
    centages
    -0.89
     tros
    -0.86
     Extent
    -0.86
     criterios
    -0.85
     temporaire
    -0.81
    焘
    -0.81
    fillment
    -0.80
    훙
    -0.80
    POSITIVE LOGITS
     Fed
    1.11
     polyn
    0.85
     and
    0.84
     Feder
    0.82
     Campan
    0.81
    รอบ
    0.77
     Fedora
    0.76
     cwd
    0.76
     FED
    0.75
     زیرا
    0.75
    Activations Density 0.015%

    No Known Activations