© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20353
    Prev
    Next
    INDEX
    Explanations

    applying for a position

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

    The neuron fires on nouns denoting things you apply for—e.g. applications, funding, positions, jobs, visas, passports, credit cards.

    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
     varandra
    -1.77
     barnen
    -1.40
     två
    -1.30
     ändå
    -1.27
     fortfarande
    -1.27
    раздо
    -1.25
     dziś
    -1.23
     nästan
    -1.23
     honom
    -1.18
    还是
    -1.17
    POSITIVE LOGITS
    attoos
    1.34
    rafa
    1.21
     he
    1.14
    ırım
    1.09
    ätten
    1.08
     such
    1.08
    balar
    1.07
    aperto
    1.06
    lím
    1.05
     hanya
    1.04
    Activations Density 0.113%

    No Known Activations