© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30790
    Prev
    Next
    INDEX
    Explanations

    suspicious financial activity detection

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

    The neuron is highly sensitive to numerical expressions—especially dollar amounts, digits, and legal statute or section citations.

    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
     archers
    -0.80
    ورية
    -0.79
    stolen
    -0.78
     successivo
    -0.77
     surrounded
    -0.74
     EXTER
    -0.72
     xhr
    -0.71
    unauthorized
    -0.71
     supporto
    -0.70
     gracefully
    -0.69
    POSITIVE LOGITS
     suspicious
    1.02
     SAR
    0.96
     threshold
    0.95
     Threshold
    0.94
     Sus
    0.94
    Threshold
    0.92
     CTR
    0.90
    sus
    0.88
     suspicion
    0.84
     sus
    0.84
    Activations Density 0.014%

    No Known Activations