© 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. 31-GEMMASCOPE-2-RES-65K
    7. 12430
    Prev
    Next
    INDEX
    Explanations

    Islamic terms and phrases

    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
    ጕ
    0.68
    িনবার্গ
    0.66
    Tennessee
    0.59
    ኵ
    0.57
    ቴክ
    0.57
    ቈ
    0.56
    Williams
    0.55
     athleticism
    0.55
     Vanderbilt
    0.55
    ቝ
    0.55
    POSITIVE LOGITS
     Allah
    1.02
     Quran
    1.01
     Alhamdulillah
    0.94
     अल्लाह
    0.87
    Quran
    0.83
     Masjid
    0.82
     Muslim
    0.81
     Muslims
    0.80
     আল্লাহ
    0.79
    ismillah
    0.79
    Activations Density 0.035%

    No Known Activations