© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73927
    Prev
    Next
    INDEX
    Explanations

    corporate domain administrator

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

    The neuron strongly activates on numeric tokens (e.g. numbers and numeric identifiers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Serum
    -1.01
    стол
    -0.99
    柢
    -0.94
     Schumer
    -0.94
     -$
    -0.94
    детская
    -0.94
     income
    -0.93
    NEM
    -0.92
    duma
    -0.92
    neus
    -0.91
    POSITIVE LOGITS
     corporate
    1.89
     employee
    1.82
     workplace
    1.68
     Employee
    1.63
    employee
    1.62
     employees
    1.61
    Employee
    1.60
     office
    1.52
     Workplace
    1.49
    Employees
    1.41
    Activations Density 0.213%

    No Known Activations