© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 52369
    Prev
    Next
    INDEX
    Explanations

    demonstrative these

    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_65k_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
     เหมาะ
    0.42
     ομάδα
    0.42
    入门
    0.40
    aucune
    0.40
    🥁
    0.40
    ご了承ください
    0.40
     отсутствует
    0.39
    7
    0.39
    人數
    0.38
    ຕ້ອງການ
    0.38
    POSITIVE LOGITS
    这些
    0.40
     hekt
    0.40
     এইসব
    0.38
     ასევე
    0.35
     ankaŭ
    0.34
    ുകൂ
    0.33
     peste
    0.33
     THESE
    0.32
    দিগকে
    0.32
    以上に
    0.32
    Activations Density 0.017%

    No Known Activations