© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129971
    Prev
    Next
    INDEX
    Explanations

    understanding specific subjects

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

    The neuron activates on occurrences of the word “understanding.”

    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
    是
    -3.47
    风
    -3.00
    可以
    -2.97
    的
    -2.78
    of
    -2.73
    多
    -2.72
    长
    -2.67
    s
    -2.67
    ☆☆☆☆
    -2.66
    ㍑
    -2.63
    POSITIVE LOGITS
    姈
    3.89
     of
    3.72
    聍
    3.39
    ญี่ป
    3.13
    除此
    3.11
    弍
    3.09
    欵
    3.09
    结语
    3.09
    趼
    3.08
    汭
    3.02
    Activations Density 0.009%

    No Known Activations