© 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. 22-GEMMASCOPE-RES-131K
    7. 28233
    Prev
    Next
    INDEX
    Explanations

    influencing policy and public opinion

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

    The neuron detects terms related to organized political advocacy and lobbying.

    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
     manier
    -1.24
    ׇ
    -1.23
    rounder
    -1.21
    ¡¡
    -1.20
    ]";
    -1.20
    ⛓
    -1.19
     batterie
    -1.17
    FromString
    -1.15
    🌒
    -1.15
    ;",
    -1.13
    POSITIVE LOGITS
    וּ
    1.38
     push
    1.37
     legislative
    1.27
     lobby
    1.24
    ִּ
    1.23
     public
    1.18
    SUPPORT
    1.15
     campaign
    1.15
    ־ה
    1.13
     support
    1.10
    Activations Density 0.065%

    No Known Activations