© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117490
    Prev
    Next
    INDEX
    Explanations

    fellow appointments and roles

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

    The neuron fires on mentions of formal program or fellowship names and titles (e.g. “Congressional Health Policy Fellowship,” “Innovative Health Care Leader Program,” 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
    隴
    -0.88
     continúas
    -0.80
    Professor
    -0.77
     tumbuhan
    -0.77
     CELEBR
    -0.76
    äldrar
    -0.76
    Quando
    -0.76
    nexo
    -0.75
    collaboration
    -0.75
    yty
    -0.74
    POSITIVE LOGITS
     fellows
    2.31
     fellowship
    2.28
     Fellow
    1.95
     Fellows
    1.95
     Fellowship
    1.92
    Fellow
    1.73
    fellow
    1.67
     fellow
    1.59
     cohort
    1.47
     fellowships
    1.40
    Activations Density 0.062%

    No Known Activations