© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8562
    Prev
    Next
    INDEX
    Explanations

    Israel and Jewish people

    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_40_width_16k_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
    讒
    0.41
     noxious
    0.40
     Fic
    0.39
     soothing
    0.37
     puriso
    0.36
    棘
    0.36
     Pelican
    0.36
    蟠
    0.36
     पाण
    0.35
     Franciscan
    0.35
    POSITIVE LOGITS
     Moses
    1.00
    以色列
    1.00
     Israël
    0.97
    Israel
    0.95
     Израи
    0.94
     Israel
    0.94
     Israelites
    0.93
    Moses
    0.92
     israel
    0.89
     Jewish
    0.80
    Activations Density 0.094%

    No Known Activations