© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27259
    Prev
    Next
    INDEX
    Explanations

    political proposals and promises

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

    The neuron fires on words and phrases related to formal politics—campaigns, policies, platforms, offices, and other electoral or legislative terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Komunikasi
    -1.27
    ׇ
    -1.26
    gewöhn
    -1.20
    ି
    -1.19
    MOQ
    -1.19
    Общие
    -1.16
     мою
    -1.13
    ㍑
    -1.13
    zysty
    -1.13
     مباراة
    -1.13
    POSITIVE LOGITS
     policy
    1.43
     promise
    1.27
     would
    1.27
     policies
    1.24
     opponent
    1.22
     Promise
    1.14
     proposed
    1.13
     promises
    1.13
     candidate
    1.13
     plans
    1.11
    Activations Density 0.027%

    No Known Activations