© 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. 85805
    Prev
    Next
    INDEX
    Explanations

    names and places starting with Gre

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

    The neuron is triggered by the substring “Gre” (i.e. tokens starting with “Gre”).

    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
    </em>
    -2.78
    茀
    -2.77
    轳
    -2.67
     a
    -2.66
    棪
    -2.61
    晙
    -2.56
    懨
    -2.53
    嫫
    -2.50
    谁能
    -2.41
    媖
    -2.41
    POSITIVE LOGITS
    0
    3.48
    a
    3.41
    '
    2.69
     ヶ
    2.42
    3
    2.33
    8
    2.31
     он
    2.27
    或者
    2.27
     {
    2.19
     те
    2.09
    Activations Density 0.005%

    No Known Activations