© 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
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 33300
    Prev
    Next
    INDEX
    Explanations

    aur, aure, gold references

    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
    يتها
    0.41
    ตอน
    0.39
    اية
    0.38
     caoutchouc
    0.38
    ሢ
    0.38
     Sunday
    0.38
    дание
    0.38
    欴
    0.37
     tren
    0.37
    一把
    0.37
    POSITIVE LOGITS
     aur
    0.68
    Aur
    0.61
     Aur
    0.59
     AUR
    0.47
    aur
    0.46
     aura
    0.46
    icular
    0.46
     Ora
    0.45
    ഞ്ച്
    0.43
    oral
    0.43
    Activations Density 0.002%

    No Known Activations