© 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. 34-GEMMASCOPE-RES-131K
    7. 92823
    Prev
    Next
    INDEX
    Explanations

    governorship election

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is highly sensitive to words and phrases related to elections and formal electoral procedures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    loài
    -0.81
    waża
    -0.77
    EIP
    -0.75
     SRL
    -0.72
     भे
    -0.71
    heus
    -0.71
    çade
    -0.70
    ↢
    -0.70
     Theologie
    -0.69
     siendo
    -0.69
    POSITIVE LOGITS
     election
    1.73
     elections
    1.70
     polls
    1.25
    élection
    1.12
     primaries
    1.11
    election
    1.07
    Election
    1.05
     Elections
    1.04
     élections
    1.03
     elecciones
    1.02
    Activations Density 0.010%

    No Known Activations