© 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. 12868
    Prev
    Next
    INDEX
    Explanations

    reporting official activities or roles

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

    The neuron strongly activates on mentions of formal authorities or institutional roles (e.g. “deputies,” “police,” “court,” “meeting,” “Department”).

    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
     Often
    -1.09
     keker
    -1.01
     Give
    -0.97
     добре
    -0.97
     Trying
    -0.94
    чать
    -0.94
     Knowing
    -0.89
     aquest
    -0.88
     tailored
    -0.88
     Creating
    -0.88
    POSITIVE LOGITS
    そうです
    1.01
     attraverso
    1.01
    もあって
    0.97
     قسم
    0.97
     搞笑
    0.94
     splendid
    0.93
    Espèce
    0.93
     alcune
    0.92
    と話
    0.92
     unending
    0.90
    Activations Density 0.020%

    No Known Activations