© 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. 27528
    Prev
    Next
    INDEX
    Explanations

    rather than

    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
     تسه
    0.42
    dokument
    0.41
     }-
    0.40
    getJSON
    0.40
     whereupon
    0.39
    يي
    0.39
    يس
    0.39
     schop
    0.39
    ᅱ
    0.38
     léč
    0.38
    POSITIVE LOGITS
     ادارے
    0.46
     ক্ষুধার
    0.45
     Sakura
    0.44
     cắt
    0.43
     अवधारणा
    0.43
     Reflection
    0.43
     এখানেই
    0.43
     bản
    0.43
     اداروں
    0.43
     Suzhou
    0.42
    Activations Density 0.012%

    No Known Activations