© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 35011
    Prev
    Next
    INDEX
    Explanations

    appointed to a role or office

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

    This neuron strongly activates on occurrences of the past‐tense copular/linking verb “was” (and similar biographical verb forms) in biography‐style sentences.

    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
    Leadership
    -1.08
    ſt
    -0.98
    leadership
    -0.93
    睜
    -0.91
     ambassade
    -0.90
     éché
    -0.89
    團隊
    -0.86
     spektak
    -0.85
     ministres
    -0.85
    ordning
    -0.84
    POSITIVE LOGITS
     superintendent
    1.39
     secretary
    1.26
     Superintendent
    1.16
     assistant
    1.10
     Super
    1.08
     chief
    1.04
     resident
    0.95
     Secretary
    0.94
     super
    0.94
    Superintendent
    0.93
    Activations Density 0.084%

    No Known Activations