© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11889
    Prev
    Next
    INDEX
    Explanations

    printable Christmas coloring pages

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

    sexual assault

    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_40_width_16k_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
    ↵
    0.41
    ・・・・
    0.41
    .......
    0.39
    ・・・。
    0.39
    ↵↵
    0.38
    と同様
    0.38
    --
    0.38
     "...
    0.37
    ………..
    0.37
    .............
    0.36
    POSITIVE LOGITS
    様専用
    0.57
     ‎
    0.45
     ‌
    0.41
    ‎
    0.41
     أ
    0.41
    为什么
    0.40
     Hôtel
    0.39
    ⁩
    0.39
    _
    0.38
     Roblox
    0.37
    Activations Density 0.714%

    No Known Activations