© 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. 10-GEMMASCOPE-RES-131K
    7. 58948
    Prev
    Next
    INDEX
    Explanations

    business

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

    The neuron strongly activates on occurrences of the word “business” (and its plural “businesses”).

    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
     Japão
    -1.84
    橚
    -1.80
     mangá
    -1.73
     castelo
    -1.70
    亖
    -1.67
     comesti
    -1.59
     Comissão
    -1.59
    孥
    -1.56
     chão
    -1.56
     again
    -1.56
    POSITIVE LOGITS
    ↵↵
    2.13
     derselben
    1.95
    they
    1.88
     They
    1.70
     schwach
    1.63
    me
    1.62
    內的
    1.61
    ”
    1.59
     родителей
    1.59
    ?”
    1.59
    Activations Density 0.026%

    No Known Activations