© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43781
    Prev
    Next
    INDEX
    Explanations

    president or chief leader

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

    This neuron detects mentions of formal leadership titles—especially when qualified by ordinals or numbers—such as “first president,” “seventh President,” “Chief Scout Executive,” “Governor,” “Principal,” or “Abbot.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     innym
    -1.27
    ',
    -1.23
     accuses
    -1.22
    ,
    
    -1.21
    𝔡
    -1.18
    Synonymes
    -1.15
     restricts
    -1.13
     declares
    -1.12
     warns
    -1.12
     defends
    -1.10
    POSITIVE LOGITS
     who
    1.73
     does
    1.45
     should
    1.21
    壹
    1.19
     after
    1.19
     while
    1.18
     seemed
    1.17
    排出
    1.17
     kyllä
    1.17
    邂
    1.16
    Activations Density 0.042%

    No Known Activations