© 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. 16-GEMMASCOPE-2-RES-262K
    7. 14216
    Prev
    Next
    INDEX
    Explanations

    enzyme function or classification

    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_16_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
    ли
    1.23
    is
    0.98
    ні
    0.92
    y
    0.89
    n
    0.87
    yana
    0.86
    liği
    0.85
    きた
    0.83
    zelfde
    0.82
    اسی
    0.80
    POSITIVE LOGITS
    I
    1.00
    O
    0.95
    ”
    0.94
     enzyme
    0.91
    ্প
    0.85
    K
    0.83
     enzymes
    0.77
    ร
    0.76
     gesund
    0.73
    ,”
    0.72
    Activations Density 0.002%

    No Known Activations