© 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-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 14462
    Prev
    Next
    INDEX
    Explanations

    motif

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     Dragons
    0.61
     അഭിപ്
    0.58
    ListOf
    0.57
     ক্ষেত্রে
    0.56
    栃
    0.52
     सरकारों
    0.52
     Dragon
    0.51
    龍
    0.51
     गांधी
    0.51
     Gandhi
    0.51
    POSITIVE LOGITS
     themed
    1.81
     motif
    1.62
    モチーフ
    1.60
    themed
    1.56
     motifs
    1.46
     theme
    1.33
     wallpaper
    1.31
    主题
    1.24
     temática
    1.24
    图案
    1.24
    Activations Density 0.228%

    No Known Activations