© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66078
    Prev
    Next
    INDEX
    Explanations

    election, vote, observation

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

    The neuron is specialized to spot mentions of political elections and their surrounding event details.

    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
     customers
    -0.93
    wakeup
    -0.73
     sufferers
    -0.72
     замести
    -0.71
     topik
    -0.68
     titles
    -0.68
     chắn
    -0.67
     Ermitt
    -0.66
    Israel
    -0.66
    输入
    -0.66
    POSITIVE LOGITS
     observation
    1.62
     Observation
    1.61
     observers
    1.56
     observer
    1.48
    observation
    1.38
    observers
    1.37
    Observers
    1.34
     Observer
    1.30
    Observation
    1.28
     наблюда
    1.28
    Activations Density 0.012%

    No Known Activations