© 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. 9955
    Prev
    Next
    INDEX
    Explanations

    take or taking

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

    The neuron fires on occurrences of the verb “take” (in its various tenses and forms).

    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
    0
    -2.81
    ↵
    -2.05
     '
    -1.91
    <em>
    -1.88
    <i>
    -1.88
    or
    -1.87
    3
    -1.87
    8
    -1.77
    <b>
    -1.74
    、
    -1.74
    POSITIVE LOGITS
    聍
    2.02
    辚
    1.93
     koning
    1.89
    摭
    1.88
    谂
    1.88
    嵎
    1.86
    釙
    1.85
    筴
    1.84
    蘩
    1.82
    槨
    1.81
    Activations Density 0.004%

    No Known Activations