© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25096
    Prev
    Next
    INDEX
    Explanations

    Congress

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

    The neuron specifically lights up on occurrences of the term “Congress” (i.e. references to the legislative body).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    甃
    -2.09
    for
    -2.06
    that
    -2.00
     They
    -1.98
     concernant
    -1.97
     bahwa
    -1.87
    LARATION
    -1.85
     habrá
    -1.84
     
    -1.84
    ୩
    -1.84
    POSITIVE LOGITS
    ܜ
    2.84
     經典
    2.59
     atlik
    2.38
     tbe
    2.38
     階段
    2.34
    ↵
    2.27
     nė
    2.27
    鏐
    2.25
    鼱
    2.22
    袛
    2.19
    Activations Density 0.010%

    No Known Activations