© 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. 34-GEMMASCOPE-RES-131K
    7. 81305
    Prev
    Next
    INDEX
    Explanations

    explain or give

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

    The neuron strongly activates on question sentences—especially on the “?” token—so it’s basically detecting questions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ごちそう
    -1.01
     bergen
    -0.91
     geze
    -0.89
     lakini
    -0.89
     alip
    -0.88
     vanille
    -0.87
    regarding
    -0.87
     vogel
    -0.85
    advised
    -0.85
     Administração
    -0.85
    POSITIVE LOGITS
     explain
    2.70
     Explain
    2.30
     give
    1.85
     why
    1.83
    Explain
    1.78
     discuss
    1.64
     explaining
    1.62
    explain
    1.59
     explains
    1.59
     Give
    1.54
    Activations Density 0.114%

    No Known Activations