© 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. 110961
    Prev
    Next
    INDEX
    Explanations

    be + caution or advice

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

    The neuron activates on the modal/imperative verb “be” when it’s used to give advice, warnings, or instructions (e.g. “be sure,” “be warned,” “be wary”).

    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
    nological
    -2.03
    :
    -1.88
    j
    -1.75
    amente
    -1.73
    "
    -1.70
    izational
    -1.70
     völ
    -1.64
     noirs
    -1.63
    thodox
    -1.59
    y
    -1.59
    POSITIVE LOGITS
     žal
    1.87
    película
    1.80
     ním
    1.70
     możesz
    1.65
     “.
    1.62
    lapsingToolbar
    1.61
    龉
    1.61
     nhưng
    1.61
    ınıza
    1.59
     “[
    1.55
    Activations Density 0.009%

    No Known Activations