© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10755
    Prev
    Next
    INDEX
    Explanations

    election ballot and recall

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

    The neuron strongly activates on words and numbers in contexts describing petition or ballot‐measure signature requirements and election/ballot 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_10/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
    
    -1.21
    kW
    -1.20
    cultura
    -1.12
     venerable
    -1.10
     этих
    -1.09
    _{
    -1.08
    ]_{\
    -1.08
    ╩
    -1.07
     wich
    -1.07
     WHICH
    -1.02
    POSITIVE LOGITS
     impedir
    1.15
     cerah
    1.09
     shouldn
    1.00
    essica
    0.99
     know
    0.98
    眈
    0.97
     อย
    0.96
    
    0.96
     chargés
    0.96
     secours
    0.95
    Activations Density 0.062%

    No Known Activations