© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7156
    Prev
    Next
    INDEX
    Explanations

    Islam, terrorism, France

    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_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
    Acceler
    0.45
    Program
    0.44
     accelerates
    0.43
    PVC
    0.42
    Prairie
    0.41
    ጪ
    0.41
    Cups
    0.40
    粽
    0.40
    Healthy
    0.40
     элемент
    0.39
    POSITIVE LOGITS
     आतंकवाद
    0.64
     Islamic
    0.62
     Islamist
    0.61
     France
    0.60
     islam
    0.57
     इस्लामिक
    0.57
     Islam
    0.56
     islamic
    0.55
     terrorists
    0.55
     terrorist
    0.54
    Activations Density 0.010%

    No Known Activations