© 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-262K
    7. 144054
    Prev
    Next
    INDEX
    Explanations

    scatter plot visualization

    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_262k_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
    行业的
    0.64
     ដែល
    0.54
    𝙤
    0.53
    地区的
    0.52
     代
    0.51
    menuCategory
    0.50
    擔任
    0.49
    單位
    0.49
     沒有
    0.48
     ຫຼື
    0.48
    POSITIVE LOGITS
    ждения
    0.44
    理
    0.43
    7
    0.43
    8
    0.43
    ックス
    0.42
     epitope
    0.41
     .)
    0.41
     *_
    0.40
     *
    0.39
    4
    0.39
    Activations Density 0.006%

    No Known Activations