© 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. 58631
    Prev
    Next
    INDEX
    Explanations

    campaign contributions and donors

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

    The neuron is tuned to detect political campaign–finance language, especially numeric figures, donation amounts, and fundraising terminology.

    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
    لام
    -0.89
    setContentView
    -0.82
     bibl
    -0.79
    DISPATCH
    -0.77
    fahrens
    -0.75
     SAVINGS
    -0.74
    需求
    -0.74
    색
    -0.73
     ANNOUNC
    -0.72
     MessageBox
    -0.71
    POSITIVE LOGITS
     contributions
    1.37
     donations
    1.27
     maxed
    1.20
     campaign
    1.20
     contribution
    1.17
     donors
    1.16
    contributions
    1.14
     contributor
    1.06
     donor
    1.05
     bund
    1.03
    Activations Density 0.020%

    No Known Activations