© 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. 22-GEMMASCOPE-RES-131K
    7. 71895
    Prev
    Next
    INDEX
    Explanations

    professional roles and responsibilities

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

    This neuron fires on tokens naming formal titles, roles, and organization affiliations (e.g. job titles and institutional names) in biographical text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     our
    -1.13
     them
    -1.05
     from
    -1.05
     either
    -1.02
     they
    -1.00
     on
    -0.99
     ellos
    -0.97
     by
    -0.95
     but
    -0.94
    :[],
    -0.94
    POSITIVE LOGITS
     duties
    1.47
     respon
    1.45
     responsible
    1.45
     tasks
    1.25
     tasked
    1.23
     responsibility
    1.17
    responsible
    1.16
     portail
    1.15
     grises
    1.14
     répertoire
    1.14
    Activations Density 0.057%

    No Known Activations