© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115666
    Prev
    Next
    INDEX
    Explanations

    voting and shareholders

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

    The neuron fires strongly on numeric and monetary tokens—digits, currency amounts, percentages, share-class labels, and other financial figures.

    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
     thánh
    -0.87
    áda
    -0.84
    ENDIAN
    -0.83
     litoral
    -0.76
    |$
    -0.75
    iose
    -0.71
    bmatrix
    -0.70
    λεί
    -0.69
    Deze
    -0.69
     Montaigne
    -0.69
    POSITIVE LOGITS
     voting
    3.59
     Voting
    2.83
    voting
    2.80
    Voting
    2.75
     votes
    2.50
     vote
    2.44
    vote
    2.20
    投票
    1.95
    votes
    1.90
    Vote
    1.89
    Activations Density 0.013%

    No Known Activations