© 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. 22-GEMMASCOPE-RES-131K
    7. 65691
    Prev
    Next
    INDEX
    Explanations

    elected officials or government positions

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

    The neuron is triggered by mentions of government or civic offices and related actions (e.g. “mayor,” “council,” “commissioner,” “resignation”).

    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
     wavering
    -1.24
     belligerent
    -1.23
     навіть
    -1.20
    گزاری
    -1.20
     dainty
    -1.18
    Using
    -1.16
     exorbitant
    -1.14
     sensuous
    -1.14
     множество
    -1.14
     worldwide
    -1.14
    POSITIVE LOGITS
     municipal
    1.31
     community
    1.30
     aktive
    1.25
     conectado
    1.24
     vê
    1.23
     residents
    1.23
     elected
    1.20
     aluminio
    1.18
    1.16
     COMMUNITY
    1.16
    Activations Density 0.031%

    No Known Activations