© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17387
    Prev
    Next
    INDEX
    Explanations

    scam or fraud related terms

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

    scams and fraud protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     symbolically
    0.43
    梏
    0.43
     বাধা
    0.42
     destruction
    0.41
     Destruction
    0.41
    uée
    0.41
    佗
    0.41
    Acknowledgments
    0.39
     শক্তি
    0.39
    缩小
    0.38
    POSITIVE LOGITS
     scam
    2.63
     scams
    2.55
     scammers
    2.53
     fraudsters
    2.28
     Scam
    2.22
    詐
    2.17
     fraudulent
    2.14
    骗
    2.14
     frauds
    2.09
     fraud
    2.03
    Activations Density 0.261%

    No Known Activations