© 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. 31-GEMMASCOPE-2-RES-262K
    7. 52804
    Prev
    Next
    INDEX
    Explanations

    measurements and multilingual text

    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/layer_31_width_262k_l0_medium
    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
     Mill
    0.49
     הכ
    0.45
     Cou
    0.44
     Larg
    0.43
     Nosotros
    0.43
     Cosa
    0.43
    飫
    0.42
    inizio
    0.42
     Phosph
    0.41
    ל
    0.41
    POSITIVE LOGITS
     pomiędzy
    0.44
    uteur
    0.44
     লক্ষ্যে
    0.42
    懵
    0.41
    ടുന്ന
    0.41
     giữa
    0.40
    ットフォーム
    0.40
     sân
    0.40
     সাম্রাজ
    0.39
     kontek
    0.39
    Activations Density 0.003%

    No Known Activations