© 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. 50124
    Prev
    Next
    INDEX
    Explanations

    voting and board decisions

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

    This neuron fires on words and phrases typical of formal meeting or legislative reports—especially voting actions, counts, and participants (e.g., “abstain,” vote tallies, board members).

    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
    辈子
    -1.13
     范
    -1.07
    INTS
    -1.06
     юно
    -1.05
     зарубе
    -1.04
     美国
    -1.02
    éhez
    -1.00
     poft
    -0.98
     بگیرید
    -0.98
    NATIONAL
    -0.98
    POSITIVE LOGITS
     vote
    1.49
     board
    1.44
     votes
    1.43
     voted
    1.42
     quorum
    1.37
     motion
    1.36
     voters
    1.34
     procedural
    1.30
     council
    1.29
     voting
    1.29
    Activations Density 0.052%

    No Known Activations