© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 26428
    Prev
    Next
    INDEX
    Explanations

    fraudulent 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_all/layer_41_width_262k_l0_big
    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
     looted
    0.37
    郤
    0.36
     NSA
    0.36
    political
    0.35
    politik
    0.35
     libertarian
    0.35
    致
    0.35
    functions
    0.35
     sécur
    0.34
     politic
    0.34
    POSITIVE LOGITS
     fraud
    1.87
     Fraud
    1.69
    Fraud
    1.63
     frauds
    1.61
    fraud
    1.59
     fraudulent
    1.54
     fraude
    1.50
     fraudsters
    1.30
    詐
    1.26
     fraudulently
    1.24
    Activations Density 0.002%

    No Known Activations