© 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. 13500
    Prev
    Next
    INDEX
    Explanations

    people in roles or groups

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

    The neuron activates on nouns naming types of workers or subordinates (e.g. craftsmen, labourers, deputies, assistants).

    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
    Both
    -0.90
    träglich
    -0.90
    Our
    -0.85
    私たちは
    -0.84
     хозя
    -0.82
     negras
    -0.81
     trinken
    -0.81
    Among
    -0.79
    From
    -0.78
    Neither
    -0.77
    POSITIVE LOGITS
     subordinates
    1.29
     subordinate
    1.23
     whom
    1.06
     followers
    1.05
     подчи
    1.02
     loyal
    1.02
     his
    1.01
     assistants
    0.97
    ⊆
    0.95
     sub
    0.93
    Activations Density 0.089%

    No Known Activations