© 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. 45577
    Prev
    Next
    INDEX
    Explanations

    Labour politicians and roles

    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
     Republican
    -0.92
     conservative
    -0.88
     directiva
    -0.85
    Elmer
    -0.83
    Republican
    -0.82
    管道
    -0.79
     BJP
    -0.77
     libertarian
    -0.76
    Wut
    -0.74
    conservative
    -0.73
    POSITIVE LOGITS
     Labour
    1.88
    Labour
    1.60
     Labor
    1.55
    Labor
    1.45
    labor
    1.17
     labor
    1.12
     Shadow
    1.11
     labour
    1.07
    Shadow
    1.05
     LABOR
    1.05
    Activations Density 0.032%

    No Known Activations