© 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. 4922
    Prev
    Next
    INDEX
    Explanations

    email sending and correspondence

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

    email communication

    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
    yielding
    0.52
     ออนไลน์
    0.42
    ungsseite
    0.41
    ウム
    0.40
    日本製
    0.40
    ｨ
    0.39
    ⌝
    0.39
    iveau
    0.39
    aties
    0.39
    actionMode
    0.39
    POSITIVE LOGITS
     correspondence
    1.12
    📧
    1.10
    邮件
    1.09
     smtp
    1.07
     mail
    1.06
     SMTP
    1.05
     sent
    1.04
    📨
    1.04
     email
    1.02
     Gmail
    1.00
    Activations Density 0.078%

    No Known Activations