© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108315
    Prev
    Next
    INDEX
    Explanations

    chief and officer titles

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

    The neuron fires most strongly on C-suite job title words (e.g. “Chief,” “Operating,” “Officer,” “CEO,” “CFO,” 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
     себя
    -0.85
     Founder
    -0.85
     proprietor
    -0.84
    anneau
    -0.79
    Founder
    -0.79
    enha
    -0.78
    ceiling
    -0.77
     SPC
    -0.77
    CENTER
    -0.76
     depot
    -0.75
    POSITIVE LOGITS
     Chief
    2.91
     chief
    2.56
    Chief
    2.53
     COO
    2.52
     CFO
    2.33
    COO
    2.09
     CHIEF
    2.08
     CTO
    1.97
    chief
    1.88
    CFO
    1.87
    Activations Density 0.035%

    No Known Activations