© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54167
    Prev
    Next
    INDEX
    Explanations

    words starting with Rou

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

    The neuron fires on any token containing the letter sequence “rou” (as in Roumania, Rousakis, Rouhani, or ROUTER).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     вікі
    -0.82
    绻
    -0.76
     quanh
    -0.74
     encompasses
    -0.73
     thicker
    -0.73
     subsections
    -0.73
     simple
    -0.71
    pannt
    -0.71
    小镇
    -0.71
     fairer
    -0.71
    POSITIVE LOGITS
    Rou
    1.15
     Rou
    0.89
    Gyro
    0.89
     Table
    0.85
    table
    0.85
    rou
    0.85
     rou
    0.84
    production
    0.84
     ルー
    0.80
     TABLE
    0.79
    Activations Density 0.011%

    No Known Activations