© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 18398
    Prev
    Next
    INDEX
    Explanations

    sermon and preach

    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_16_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
    า
    1.29
    ai
    1.27
    au
    1.26
    ang
    1.08
    س
    1.02
    SA
    1.00
    IN
    0.98
    de
    0.96
    ian
    0.96
    af
    0.95
    POSITIVE LOGITS
     preached
    1.23
    تي
    1.17
     preach
    1.04
     preaching
    1.01
    ти
    1.00
     preachers
    0.97
     preacher
    0.92
    </h3>
    0.86
    ير
    0.86
    ذي
    0.84
    Activations Density 0.001%

    No Known Activations