© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113848
    Prev
    Next
    INDEX
    Explanations

    words starting with "Re"

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

    The neuron activates on tokens beginning with the uppercase letters “Re” (i.e., words or names prefixed by “Re”).

    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
    zembro
    -2.88
    .
    -2.64
     旅游
    -2.53
    ꯹
    -2.50
    缈
    -2.48
    .")
    -2.34
    𓋼
    -2.33
     风景
    -2.28
     کردن
    -2.27
    juries
    -2.19
    POSITIVE LOGITS
     
    2.95
    一個
    2.66
     بينما
    2.58
    ン
    2.58
     {
    2.58
     بالإضافة
    2.53
    н
    2.47
    ～～
    2.44
    ～～～
    2.36
    は
    2.36
    Activations Density 0.013%

    No Known Activations