© 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. 6776
    Prev
    Next
    INDEX
    Explanations

    money laundering and crime

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

    The main thing this neuron does is detect mentions of money-laundering and related anti–money-laundering policy terms.

    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
     succès
    -1.45
     :).
    -1.25
     plancher
    -1.21
     någon
    -1.18
     magasiner
    -1.17
     BEGINNING
    -1.17
     enthou
    -1.17
     maïs
    -1.17
     meub
    -1.12
     tournage
    -1.12
    POSITIVE LOGITS
     from
    1.38
     using
    1.17
    边的
    1.15
     çeşitli
    1.13
    قرأ
    1.12
     praising
    1.11
     used
    1.10
     financing
    1.09
     featuring
    1.09
    ↵
    1.08
    Activations Density 0.033%

    No Known Activations