© 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. 104936
    Prev
    Next
    INDEX
    Explanations

    questions starting with "What are"

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

    The neuron strongly activates on interrogative phrases—especially questions beginning with “What are…”

    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
    </
    -1.78
    >
    -1.76
    What
    -1.71
    la
    -1.70
    ")
    -1.70
    同じ
    -1.67
    如同
    -1.63
     occur
    -1.54
     månader
    -1.53
    Does
    -1.51
    POSITIVE LOGITS
    岽
    2.09
    ໊
    1.88
    鵟
    1.82
    嗖
    1.80
    ⟝
    1.79
    舸
    1.72
    撄
    1.70
    ländischen
    1.65
    閦
    1.64
    鑁
    1.63
    Activations Density 0.007%

    No Known Activations