© 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. 15618
    Prev
    Next
    INDEX
    Explanations

    questions and specific terms

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

    improved code and multilingual phrases

    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
    ↵↵
    0.39
    ！！
    0.38
    以及
    0.38
    ،
    0.38
    also
    0.38
    および
    0.37
    ↵↵↵↵↵
    0.37
    및
    0.36
    。
    0.36
    、
    0.36
    POSITIVE LOGITS
     използ
    0.36
     মুদ্রা
    0.35
     इस्तीफा
    0.35
     уйнарга
    0.34
    <unused582>
    0.32
     funcionários
    0.32
     ನೀರಿನ
    0.32
    <unused552>
    0.32
     zigzag
    0.31
     फूलों
    0.31
    Activations Density 0.037%

    No Known Activations