© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56789
    Prev
    Next
    INDEX
    Explanations

    election candidates

    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
    Negative Logits
     Nigeria
    -0.84
    Nigeria
    -0.81
    ╕
    -0.80
    Nation
    -0.75
     Nigerians
    -0.73
     Shou
    -0.73
    äsident
    -0.72
     postural
    -0.71
     polskich
    -0.71
     ਕੀ
    -0.71
    POSITIVE LOGITS
     Aspir
    1.03
     aspirants
    1.01
     primaries
    0.95
     sen
    0.93
     candidate
    0.91
     candidacy
    0.90
     aspirant
    0.89
     party
    0.88
    candidate
    0.85
     ticket
    0.82
    Activations Density 0.012%

    No Known Activations