© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8023
    Prev
    Next
    INDEX
    Explanations

    phishing emails and email content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
    粥
    1.05
     Baxter
    1.03
     Osbourne
    1.00
    Baxter
    0.98
     Wadi
    0.98
     DVR
    0.97
     Vivo
    0.95
    Walker
    0.94
    甪
    0.93
     Волго
    0.93
    POSITIVE LOGITS
     SMTP
    2.48
     mail
    2.45
    SMTP
    2.39
     Mail
    2.39
     smtp
    2.38
     MAIL
    2.36
    Mailer
    2.36
     mails
    2.36
    Mail
    2.33
    mail
    2.30
    Activations Density 0.624%

    No Known Activations