© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 17040
    Prev
    Next
    INDEX
    Explanations

    development, investment, and technology

    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
     nipples
    0.50
    镙
    0.50
     مسئلہ
    0.48
     правильно
    0.47
    ègues
    0.46
    说过
    0.46
    绦
    0.46
     иногда
    0.45
     آسی
    0.45
    庀
    0.45
    POSITIVE LOGITS
     livestream
    0.55
    精准
    0.55
    抖音
    0.55
    打造
    0.54
    颜值
    0.54
     metaverse
    0.52
    新能源
    0.52
    国産
    0.51
     estreia
    0.50
    深度
    0.50
    Activations Density 0.061%

    No Known Activations