© 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. 63491
    Prev
    Next
    INDEX
    Explanations

    Israel and its people

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly fires on the structural markers and labels that introduce or number verses/sections (e.g. verse numbers, chapter headings, and other canonical reference tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Adjustment
    -0.84
    skys
    -0.76
     malaria
    -0.73
     kaldı
    -0.72
    adjustment
    -0.71
     SYNC
    -0.71
    ហ
    -0.71
     and
    -0.70
    няться
    -0.69
     adjustment
    -0.69
    POSITIVE LOGITS
     Israel
    3.64
    Israel
    2.91
     Израи
    2.02
     israel
    1.95
    israel
    1.88
     ISRAEL
    1.84
    以色列
    1.83
     Israelites
    1.83
     ישראל
    1.81
     Israël
    1.70
    Activations Density 0.023%

    No Known Activations