© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59548
    Prev
    Next
    INDEX
    Explanations

    government agencies and organizations

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

    The neuron strongly activates on mentions of government or official regulatory bodies (e.g. council, EPA, FDA, CDC).

    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
    8
    -1.27
    9
    -1.27
    4
    -1.23
     mentales
    -1.16
    orylation
    -1.15
    beforeAll
    -1.14
     tą
    -1.12
    閪
    -1.11
    7
    -1.11
    楽しめます
    -1.11
    POSITIVE LOGITS
     between
    1.41
     sonriente
    1.33
     then
    1.27
     rápidamente
    1.23
    
    1.22
     simpan
    1.21
     elsewhere
    1.20
     dotato
    1.20
     across
    1.20
     daarna
    1.20
    Activations Density 0.204%

    No Known Activations