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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110742
    Prev
    Next
    INDEX
    Explanations

    Israel places and things

    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
    היו
    -0.99
    איך
    -0.89
     סס
    -0.87
    הגב
    -0.84
     Quran
    -0.82
     african
    -0.82
    Bism
    -0.75
    シス
    -0.73
     parishioners
    -0.73
    kunde
    -0.72
    POSITIVE LOGITS
     Israeli
    3.13
     Israel
    2.97
    Israel
    2.81
    Israeli
    2.75
     Israelis
    2.59
    以色列
    2.13
     ISRAEL
    2.11
     israel
    2.08
     Израи
    2.05
    israel
    1.90
    Activations Density 0.088%

    No Known Activations