© 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-262K
    4. 29602
    Prev
    Next
    INDEX
    Explanations

    Vedic graduates and Oxford alumni

    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
     Sinh
    0.40
    Arsenal
    0.39
     Kurdish
    0.39
    InfoHeader
    0.39
    ፅ
    0.39
     ሁሉ
    0.38
     పెట్టు
    0.38
    軫
    0.38
    歙
    0.38
     feudal
    0.38
    POSITIVE LOGITS
     शिका
    0.45
     священ
    0.45
     Graduates
    0.45
     വേദ
    0.44
     alumni
    0.44
    ্যাম
    0.44
     кукуру
    0.43
     Они
    0.43
     graduate
    0.42
     graduates
    0.42
    Activations Density 0.016%

    No Known Activations