© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30227
    Prev
    Next
    INDEX
    Explanations

    money laundering and illicit financial activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     રા
    0.54
    手术
    0.51
    干扰
    0.51
    损伤
    0.50
    胫
    0.49
    杀死
    0.49
    影响
    0.48
    动画
    0.48
    钧
    0.48
    苕
    0.47
    POSITIVE LOGITS
     laundering
    0.70
     AML
    0.69
     banking
    0.66
     laund
    0.61
     transactions
    0.61
    銀行
    0.60
     cryptocur
    0.59
     illicit
    0.59
     KYC
    0.58
     money
    0.57
    Activations Density 0.046%

    No Known Activations