© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49644
    Prev
    Next
    INDEX
    Explanations

    scamphishingfraud

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

    phishing and scams

    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_31_width_262k_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
     roots
    0.50
     coords
    0.46
     anuv
    0.45
     mutants
    0.44
    coords
    0.43
    髻
    0.43
    Roots
    0.43
     slopes
    0.42
     welds
    0.42
     medir
    0.41
    POSITIVE LOGITS
     scammers
    1.16
     scam
    1.05
     scams
    1.05
     phishing
    1.04
     fraudsters
    1.00
    骗
    0.95
    詐
    0.94
     Scam
    0.93
    诈
    0.90
    騙
    0.88
    Activations Density 0.094%

    No Known Activations