© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86161
    Prev
    Next
    INDEX
    Explanations

    thriving

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

    The main thing this neuron does is detect occurrences of the word “thrive” (e.g., “thriving,” “thrive”).

    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
    扨
    -2.97
    atother
    -2.91
    崤
    -2.89
    鸲
    -2.80
    鑁
    -2.73
    玧
    -2.66
    憍
    -2.55
    錵
    -2.45
    泚
    -2.45
    嫺
    -2.45
    POSITIVE LOGITS
    ;
    3.22
    .
    3.05
    )
    2.63
    获取
    2.48
     
    2.38
    {
    2.31
     But
    2.27
    Also
    2.25
    --
    2.22
    𝐒
    2.22
    Activations Density 0.002%

    No Known Activations