© 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. 41765
    Prev
    Next
    INDEX
    Explanations

    names starting with Gou

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

    The neuron fires on the letter sequence “gou,” as in words like “gouging.”

    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
    {
    -4.78
    ING
    -2.86
    l
    -2.81
    </b>
    -2.78
    ’
    -2.59
    S
    -2.53
    鼉
    -2.53
    ers
    -2.53
     That
    -2.50
    ।
    -2.48
    POSITIVE LOGITS
    愎
    3.06
     serão
    2.63
    廡
    2.56
    穑
    2.56
     Diſ
    2.53
    屨
    2.50
     serán
    2.45
     magnética
    2.44
    曩
    2.44
     prépare
    2.42
    Activations Density 0.002%

    No Known Activations