© 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. 40-GEMMASCOPE-2-RES-262K
    7. 17389
    Prev
    Next
    INDEX
    Explanations

    from ... to

    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_40_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
    ですし
    0.45
    䣨
    0.40
    لیکن
    0.40
    但是
    0.39
     tuttavia
    0.39
     പക്ഷേ
    0.39
     होंगे
    0.38
    kipun
    0.38
     거고
    0.38
    त्रेयी
    0.38
    POSITIVE LOGITS
     إلى
    1.30
    到
    1.30
     الى
    1.12
     to
    0.98
     kepada
    0.96
     到
    0.90
     đến
    0.88
    到一个
    0.83
     into
    0.81
     към
    0.79
    Activations Density 0.052%

    No Known Activations