© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 21859
    Prev
    Next
    INDEX
    Explanations

    macro and preprocessing definitions

    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_all/layer_41_width_262k_l0_big
    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
    skateboard
    0.42
    ريكي
    0.42
    ুইস
    0.41
    ⇣
    0.41
    IGNED
    0.40
    neutrophiles
    0.39
    setDefault
    0.39
    athletics
    0.39
    CLEAR
    0.38
    的管理
    0.38
    POSITIVE LOGITS
     macro
    1.08
     Macro
    1.05
     macros
    1.05
     Macros
    0.99
    Macro
    0.92
    macro
    0.91
    Macros
    0.89
    宏
    0.87
     preprocessing
    0.80
     preprocess
    0.78
    Activations Density 0.005%

    No Known Activations