© 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. 41-GEMMASCOPE-2-RES-262K
    7. 24012
    Prev
    Next
    INDEX
    Explanations

    west bank, jerusalem, occupied

    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_all/layer_41_width_262k_l0_big
    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
    রাষ্ট্র
    0.40
     asymmetrical
    0.36
     رع
    0.35
    zię
    0.35
    AsUpIndicator
    0.34
    apons
    0.34
    國際
    0.33
    耆
    0.33
    雷
    0.33
     जहाज
    0.33
    POSITIVE LOGITS
     West
    0.88
     Occup
    0.86
     occupied
    0.85
    occupied
    0.75
    West
    0.73
    Occup
    0.70
     ocup
    0.68
     occupé
    0.66
     occupy
    0.66
     वेस्ट
    0.64
    Activations Density 0.001%

    No Known Activations