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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15618
    Prev
    Next
    INDEX
    Explanations

    Mail

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
     bhp
    0.66
     ș
    0.61
     Cowboys
    0.59
     সড়ক
    0.59
     इनाम
    0.59
     Packers
    0.57
     mum
    0.56
     TIMES
    0.55
     Chronicle
    0.55
    "]).
    0.54
    POSITIVE LOGITS
    Mail
    1.19
     Mail
    1.06
     mail
    0.98
     MAIL
    0.96
    MAIL
    0.91
    mail
    0.90
    Scroll
    0.83
     mails
    0.77
     Scroll
    0.76
    邮件
    0.75
    Activations Density 0.006%

    No Known Activations