© 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. 66831
    Prev
    Next
    INDEX
    Explanations

    Union, Council, Mayor, Grand Patron, Her Royal Highness

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

    The neuron detects mentions of formal governmental or institutional proper names.

    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
    ⫹
    -1.41
     chré
    -1.16
     probably
    -1.14
    Ghz
    -1.10
     a
    -1.05
     any
    -1.05
     katholischen
    -1.05
     musées
    -1.03
    :
    -1.03
     because
    -1.01
    POSITIVE LOGITS
     yesterday
    1.45
     pursuant
    1.39
     climático
    1.31
     today
    1.30
     of
    1.23
    ּוֹ
    1.18
    licative
    1.16
     efficaces
    1.12
     pájaros
    1.12
    ifflin
    1.12
    Activations Density 0.028%

    No Known Activations