© 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. 34-GEMMASCOPE-RES-131K
    7. 77071
    Prev
    Next
    INDEX
    Explanations

    vote or voting

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

    The neuron strongly activates on tokens in contexts announcing or inviting public voting for awards or category nominations (e.g. “Awards,” “categories,” “online,” “voting,” “nominate,” etc.).

    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
    StatusLabel
    -1.02
    FileStream
    -0.82
    },[])
    -0.81
    之事
    -0.80
     Gespräch
    -0.80
    犷
    -0.79
    utang
    -0.77
    brot
    -0.77
    𝑸
    -0.76
    Valor
    -0.75
    POSITIVE LOGITS
     voting
    4.88
     vote
    4.56
     votes
    4.50
     voted
    3.75
    Voting
    3.64
     Voting
    3.55
    vote
    3.42
    voting
    3.41
    投票
    3.38
    Vote
    3.36
    Activations Density 0.065%

    No Known Activations