© 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. 10-GEMMASCOPE-RES-131K
    7. 68539
    Prev
    Next
    INDEX
    Explanations

    tax advantages and retirement plans

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

    The main thing this neuron does is spot mentions of tax‐related terms and concepts.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     luxem
    -1.84
     uruguay
    -1.82
    +/*
    -1.70
     accommodates
    -1.68
     ecuador
    -1.66
     rosario
    -1.66
    iconductors
    -1.64
    quelize
    -1.63
    犸
    -1.58
    之后的
    -1.57
    POSITIVE LOGITS
     zijn
    1.84
    战胜
    1.84
     ursprünglichen
    1.78
     często
    1.74
     vorliegenden
    1.66
     maravillosas
    1.66
    ynek
    1.58
     hermosas
    1.57
     üblichen
    1.56
    cosas
    1.55
    Activations Density 0.016%

    No Known Activations