© 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-65K
    7. 6202
    Prev
    Next
    INDEX
    Explanations

    survival and refugees

    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
    流畅
    0.52
    观点
    0.44
    总是
    0.43
    รูปแบบ
    0.43
     ውጤ
    0.43
    讨论
    0.43
    定义
    0.42
    囤
    0.42
    编辑
    0.41
     bold
    0.41
    POSITIVE LOGITS
     survival
    0.79
     desesper
    0.75
     sobreviv
    0.72
     sobrevivir
    0.72
     Survival
    0.70
     starvation
    0.69
     refugees
    0.68
     survivors
    0.66
    survival
    0.66
     supervivencia
    0.66
    Activations Density 0.099%

    No Known Activations