© 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. 99714
    Prev
    Next
    INDEX
    Explanations

    Have you

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

    This neuron specifically activates on the word “Have,” especially when it begins a sentence.

    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
    ]
    -2.28
    A
    -1.87
     プラス
    -1.87
    可以
    -1.86
    J
    -1.84
    i
    -1.78
    อาจ
    -1.74
     Sperm
    -1.73
    笕
    -1.73
     特別
    -1.72
    POSITIVE LOGITS
    ᯅ
    2.38
    ’.
    2.30
     dejected
    2.08
    <>(
    2.06
     They
    2.06
     uſed
    2.03
    …’
    1.98
     dick
    1.97
    市的
    1.95
    !’
    1.93
    Activations Density 0.012%

    No Known Activations