© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128446
    Prev
    Next
    INDEX
    Explanations

    ministers or Ministerial appointments

    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_10/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
     самая
    -2.36
     \
    -1.89
     процессов
    -1.88
     Other
    -1.87
    öbb
    -1.78
     milyen
    -1.77
     wichtigste
    -1.77
     menyebabkan
    -1.76
     інших
    -1.73
    árias
    -1.72
    POSITIVE LOGITS
     ministers
    3.05
    .
    2.17
    できる
    2.17
    Примеча
    2.14
    The
    2.09
     []
    2.05
    </i>
    2.03
    Estos
    1.97
    Según
    1.95
     الذي
    1.92
    Activations Density 0.003%

    No Known Activations