© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13882
    Prev
    Next
    INDEX
    Explanations

    noting and stating

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

    The neuron fires on present-participle verbs ending in “-ing,” particularly discourse-marker gerunds like “noting” and “outlining.”

    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
     cinese
    -3.22
    s
    -2.94
     illustrationer
    -2.72
    鲼
    -2.66
    的
    -2.59
    😲
    -2.59
     الموضوع
    -2.56
    💜
    -2.52
    💕
    -2.47
     なし
    -2.42
    POSITIVE LOGITS
    ING
    3.02
     noting
    2.98
    要不是
    2.67
    
    2.66
     depicting
    2.66
     choć
    2.66
    摇了
    2.58
    掟
    2.55
    揶
    2.53
    ญี่ป
    2.52
    Activations Density 0.006%

    No Known Activations