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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 146063
    Prev
    Next
    INDEX
    Explanations

    Muslim identity and multiculturalism

    np_acts-logits-general · gemini-2.5-flash-lite

    Okay, basic, Muslim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ид
    0.58
    ида
    0.53
     banyaknya
    0.52
     naka
    0.51
    ﾓ
    0.49
     maaf
    0.48
     mao
    0.48
     daca
    0.48
    кар
    0.48
     minions
    0.48
    POSITIVE LOGITS
     Muslim
    0.48
     Multicultural
    0.48
     Muslims
    0.46
    其实
    0.46
     মুসলিম
    0.45
    Actually
    0.45
    ই
    0.45
     Microbi
    0.45
     Pharma
    0.45
     مسلمان
    0.44
    Activations Density 0.001%

    No Known Activations