© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66159
    Prev
    Next
    INDEX
    Explanations

    questioning sanity or judgment

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

    The neuron is specialized to detect informal exclamatory words or phrases expressing incredulity or craziness (e.g. “nuts,” “mad,” “crazy,” “serious,” “joking”).

    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
     薬局
    -1.48
     mauva
    -1.39
     gara
    -1.38
     läm
    -1.37
     blir
    -1.35
    扨
    -1.34
    こんな感じで
    -1.34
    kinda
    -1.30
     rése
    -1.30
    SCHEME
    -1.28
    POSITIVE LOGITS
     which
    1.71
     if
    1.45
    abilidade
    1.43
     not
    1.39
     to
    1.31
     During
    1.30
     Throughout
    1.30
     این
    1.25
    osgi
    1.23
     даже
    1.21
    Activations Density 0.013%

    No Known Activations