© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 2837
    Prev
    Next
    INDEX
    Explanations

    islam or muslims questioned

    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
    在
    0.88
    x
    0.86
    ৫
    0.81
    ও
    0.77
    i
    0.75
    m
    0.74
    ich
    0.73
    沒有
    0.71
    p
    0.69
    และ
    0.68
    POSITIVE LOGITS
     Muslims
    0.98
     Islam
    0.91
     an
    0.79
     islam
    0.77
    )
    0.77
     Muslim
    0.74
     mortals
    0.74
     முஸ்
    0.74
    ↵
    0.73
     islamic
    0.72
    Activations Density 0.006%

    No Known Activations