© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31671
    Prev
    Next
    INDEX
    Explanations

    Islamic terms and Muslims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mechanism
    -0.97
     Jewish
    -0.89
     kony
    -0.87
    Jewish
    -0.85
     mechanism
    -0.84
     Israeli
    -0.82
     евре
    -0.81
     Israelis
    -0.78
     churches
    -0.78
     Torah
    -0.77
    POSITIVE LOGITS
     Muslim
    1.88
     Islam
    1.75
     Islamic
    1.69
    Muslim
    1.59
     Muslims
    1.55
    Islam
    1.41
    Islamic
    1.38
    Muslims
    1.18
     muslim
    1.17
     musul
    1.16
    Activations Density 0.029%

    No Known Activations