© 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. 102227
    Prev
    Next
    INDEX
    Explanations

    geopolitical and strategic information

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

    This neuron responds to “geo-”–related terms, particularly mentions of geopolitics or geo-economic contexts.

    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
    ፨
    -2.23
    夤
    -2.23
    氿
    -2.13
    StoryboardSegue
    -2.11
    尨
    -2.09
    orsese
    -2.05
    銠
    -2.02
    lblNewLabel
    -2.02
    狁
    -2.02
    怎么回事
    -1.99
    POSITIVE LOGITS
    (
    2.45
    f
    2.36
    0
    2.16
    {
    2.00
    K
    1.99
    O
    1.93
    v
    1.90
    W
    1.87
    H
    1.85
    //
    1.84
    Activations Density 0.005%

    No Known Activations