© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56956
    Prev
    Next
    INDEX
    Explanations

    embassy relocation

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

    The neuron strongly activates on named geopolitical entities and key political terms (e.g. country names, political figures, or high-level policy events).

    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
     všechno
    -0.79
     get
    -0.75
     impressive
    -0.74
    女人
    -0.73
     giường
    -0.72
    左边
    -0.70
    目
    -0.69
     möchtest
    -0.69
    ภาค
    -0.68
    ++;
    -0.68
    POSITIVE LOGITS
     Jerusalem
    1.28
     relocation
    1.12
     relocate
    1.02
    Jerusalem
    1.02
     relocated
    1.00
    遷
    0.96
     embassy
    0.94
     relocating
    0.90
     перене
    0.85
    Moved
    0.83
    Activations Density 0.010%

    No Known Activations