© 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. 105572
    Prev
    Next
    INDEX
    Explanations

    work contexts

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

    The neuron strongly activates on the token “work.”

    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
    銀座
    -1.21
     exactement
    -1.17
     売
    -1.16
     проблемы
    -1.12
    Person
    -1.08
     again
    -1.07
     you
    -1.04
    新宿
    -1.04
    мая
    -1.03
    ご利用
    -1.03
    POSITIVE LOGITS
    $<$
    1.45
    ).
    1.40
    Véxase
    1.30
     invigor
    1.30
    ætte
    1.21
    ֶה
    1.21
    loggedin
    1.21
    itself
    1.19
    genheiten
    1.18
    韌
    1.18
    Activations Density 0.039%

    No Known Activations