© 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. 113477
    Prev
    Next
    INDEX
    Explanations

    government departments and services

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

    This neuron detects occurrences of formal government or agency names, especially multiword titles like “Department of …,” “State Board of …,” or other official institutional headings.

    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
    (")");
    -1.52
    -
    -1.40
     jovial
    -1.34
    !
    -1.32
    {
    -1.28
     starker
    -1.28
     Lately
    -1.25
    }}}{
    -1.23
     n
    -1.22
    :
    -1.21
    POSITIVE LOGITS
     comprometido
    1.48
     seguras
    1.48
     decorado
    1.45
     fotográfico
    1.44
     corretto
    1.43
     automático
    1.42
     deportivas
    1.41
    ázky
    1.41
     eléctricas
    1.40
     envíos
    1.40
    Activations Density 0.060%

    No Known Activations