© 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. 10-GEMMASCOPE-RES-131K
    7. 73424
    Prev
    Next
    INDEX
    Explanations

    referendum events and votes

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

    The neuron fires on mentions of “referendum” (and its variants), i.e. tokens referring to public votes or referenda.

    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
     first
    -2.27
     Можно
    -2.11
     erste
    -2.11
    achuca
    -2.09
     использовании
    -2.06
    así
    -2.06
    KeyId
    -2.05
    澂
    -2.03
    渕
    -2.03
    igual
    -2.03
    POSITIVE LOGITS
    X
    2.80
     itſelf
    2.22
    </strong>
    2.20
    (
    2.20
    ൎ
    2.16
    蕺
    2.11
    珢
    2.11
    e
    2.11
    a
    2.06
    ↵↵
    2.03
    Activations Density 0.002%

    No Known Activations