© 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. 34-GEMMASCOPE-RES-131K
    7. 59252
    Prev
    Next
    INDEX
    Explanations

    Comptroller and Controller roles

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

    The neuron detects mentions of government financial‐oversight job titles (e.g. “comptroller,” “auditor,” “chief city auditor,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ♑
    -0.82
    eneration
    -0.75
    bourn
    -0.73
    สม
    -0.73
    skiego
    -0.71
    ندی
    -0.70
    ウェー
    -0.70
    mates
    -0.70
     Dickey
    -0.70
    ARDS
    -0.69
    POSITIVE LOGITS
     Comptroller
    3.28
     compt
    2.98
     controller
    2.69
     Controller
    2.66
    controller
    2.30
    Controller
    2.06
     controllers
    1.96
     Controllers
    1.82
    CONTROLLER
    1.78
     Compt
    1.72
    Activations Density 0.056%

    No Known Activations