© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9311
    Prev
    Next
    INDEX
    Explanations

    dates in November 2023

    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_31_width_16k_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
     ধর
    0.40
    的同时
    0.38
    光
    0.38
    ใช้
    0.38
    事实上
    0.37
    好き
    0.37
    0
    0.37
    ρό
    0.36
    лені
    0.36
    <0xDF>
    0.35
    POSITIVE LOGITS
    )،
    0.45
    𝗠
    0.42
    𝗣
    0.38
    𝗬
    0.38
     Unemployment
    0.38
    𝗪
    0.37
     erythematosus
    0.37
    𝙍
    0.37
    𝐌
    0.36
    ಲೀ
    0.36
    Activations Density 0.039%

    No Known Activations