© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2600
    Prev
    Next
    INDEX
    Explanations

    drafting emails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ungsseite
    0.51
    нки
    0.43
    雰
    0.43
    ično
    0.42
    வி
    0.41
    aties
    0.41
    너지
    0.41
    ankt
    0.41
    ériment
    0.41
    cendo
    0.40
    POSITIVE LOGITS
     email
    0.92
     emails
    0.91
     Email
    0.88
    📧
    0.83
    Email
    0.81
     Emails
    0.79
     correspondence
    0.76
     Gmail
    0.72
     EMAIL
    0.70
    Gmail
    0.69
    Activations Density 0.029%

    No Known Activations