© 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. 7262
    Prev
    Next
    INDEX
    Explanations

    election fraud and contested elections

    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
    ümer
    -0.76
    Biografía
    -0.75
    南浔
    -0.73
     Egal
    -0.73
    una
    -0.71
     Demolition
    -0.71
    illis
    -0.70
     croissants
    -0.69
     Uninstall
    -0.69
    お楽しみに
    -0.69
    POSITIVE LOGITS
     disputed
    1.41
     election
    1.25
     post
    1.09
     Election
    1.03
     poste
    0.94
    Election
    0.91
     Fraud
    0.89
     contested
    0.89
     electoral
    0.86
    election
    0.86
    Activations Density 0.012%

    No Known Activations