© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30970
    Prev
    Next
    INDEX
    Explanations

    indicating corrections or non-standard usage

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

    list item markers OR section separators

    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_31_width_262k_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
     niets
    0.40
    ↵↵↵
    0.38
    ↵
    0.38
     Araújo
    0.38
     composto
    0.38
     oftentimes
    0.37
    <start_of_image>
    0.37
    変換
    0.37
    %,
    0.36
    POSITIVE LOGITS
    führung
    0.46
     ಡೇ
    0.41
    ાળ
    0.40
     اوم
    0.40
    დე
    0.39
     টাইগার
    0.39
    PlayerDataCache
    0.38
     dikeluarkan
    0.38
    blueberry
    0.38
     hydrates
    0.38
    Activations Density 0.001%

    No Known Activations