Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 27895
    Prev
    Next
    INDEX
    Explanations

    corporal punishment

    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
     நேரம்
    0.44
    数据
    0.44
    表
    0.43
    爱情
    0.42
     Aplikasi
    0.41
     ডিসেম্বর
    0.41
    另一个
    0.41
     spettac
    0.41
     emocionante
    0.41
    文件
    0.40
    POSITIVE LOGITS
     população
    0.46
     prerog
    0.46
     puriso
    0.45
    人數
    0.43
    ؤلاء
    0.43
    াদিগকে
    0.42
     hereditary
    0.41
     reformers
    0.41
    ୁ
    0.40
     discriminatory
    0.40
    Activations Density 0.011%

    No Known Activations