© 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. 119097
    Prev
    Next
    INDEX
    Explanations

    John Boehner and House leadership

    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
     senate
    -0.77
    谧
    -0.73
    clays
    -0.72
    Senate
    -0.70
     المؤ
    -0.68
    mw
    -0.68
     estates
    -0.67
    Sen
    -0.67
     Senate
    -0.65
     McCain
    -0.65
    POSITIVE LOGITS
     McCarthy
    1.20
     Speaker
    1.13
     House
    1.09
     speaker
    1.02
    JECTION
    0.98
     NR
    0.93
    Speaker
    0.93
    speaker
    0.89
     kevin
    0.87
    House
    0.85
    Activations Density 0.016%

    No Known Activations