© 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. 54336
    Prev
    Next
    INDEX
    Explanations

    government control and regulation

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

    This neuron detects mentions of government or state power (e.g. terms like “government,” “small government,” “state,” or discussions of expanding or limiting government authority”).

    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
     voyez
    -1.25
    跄
    -1.23
    EVP
    -1.09
     pensez
    -1.05
     transición
    -1.04
    globalData
    -1.01
    lottesville
    -1.01
    ichtung
    -0.99
    พ์
    -0.99
    groep
    -0.98
    POSITIVE LOGITS
     Examples
    1.16
     hingegen
    1.13
     control
    1.09
     we
    1.08
    ↵↵↵
    1.04
     séparation
    1.00
     controls
    0.96
     правительства
    0.93
     unnecessary
    0.93
    Examples
    0.93
    Activations Density 0.030%

    No Known Activations