© 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. 10-GEMMASCOPE-RES-131K
    7. 104391
    Prev
    Next
    INDEX
    Explanations

    alliance and allied groups

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

    The neuron activates on mentions of alliances or coalitions (the word “alliance” and related contexts of groups joining or allying).

    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
     большая
    -2.06
    ༀ
    -2.00
     »)
    -1.96
     wohin
    -1.94
    拮
    -1.93
    itettura
    -1.92
    僞
    -1.87
     taxe
    -1.84
    .
    -1.84
    deinit
    -1.80
    POSITIVE LOGITS
    up
    2.42
    没有
    2.14
     of
    2.13
    虽
    2.05
    _
    2.02
    訫
    2.00
    卺
    1.97
    A
    1.87
    ２
    1.86
    谁
    1.82
    Activations Density 0.012%

    No Known Activations