© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 2336
    Prev
    Next
    INDEX
    Explanations

    numbers and links

    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
     эшлә
    0.38
    案内
    0.38
     ያለ
    0.36
    isyen
    0.35
    वत्ता
    0.34
    牌
    0.34
    :";
    0.33
     هنعمل
    0.33
    ŠE
    0.33
    卷
    0.33
    POSITIVE LOGITS
    ছেন
    0.32
     seorang
    0.31
     intuition
    0.29
    кти
    0.29
     inversion
    0.29
     نتی
    0.28
    䪱
    0.28
    الأ
    0.27
    জ্জ
    0.26
     virtue
    0.26
    Activations Density 0.047%

    No Known Activations