© 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. 104327
    Prev
    Next
    INDEX
    Explanations

    outlined plans and studies

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

    The neuron fires on the verb “outline” (in its various inflected forms like “outlined” or “outlines”).

    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
    {
    -4.03
     you
    -3.14
    <
    -2.84
    2
    -2.72
     to
    -2.64
    A
    -2.59
    }^{
    -2.47
     就是
    -2.39
    </i>
    -2.34
    </
    -2.31
    POSITIVE LOGITS
    だけです
    2.91
    神
    2.78
    夘
    2.66
    郿
    2.58
    媖
    2.56
    ?"
    2.53
     lidé
    2.50
     personalidade
    2.50
    䉴
    2.48
    是非常
    2.47
    Activations Density 0.003%

    No Known Activations