© 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. 10-GEMMASCOPE-RES-131K
    7. 59277
    Prev
    Next
    INDEX
    Explanations

    General Assembly and Security Council

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

    The neuron activates on occurrences of the phrase “General Assembly.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     is
    -1.94
    the
    -1.87
    ")
    -1.78
    」
    -1.69
    汌
    -1.66
    ",
    -1.64
    ۳
    -1.63
    icznej
    -1.63
     cuando
    -1.60
     estos
    -1.59
    POSITIVE LOGITS
     him
    1.63
    ویر
    1.41
    の地
    1.35
    נסת
    1.34
    まぁ
    1.34
    ヤバ
    1.33
     nouvelles
    1.31
     remercier
    1.31
    stainless
    1.30
     to
    1.30
    Activations Density 0.003%

    No Known Activations