© 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. 34-GEMMASCOPE-RES-131K
    7. 83699
    Prev
    Next
    INDEX
    Explanations

    Eudragit electro Transformation Hugh

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    哎呀
    -1.27
     gambe
    -1.09
    卧槽
    -1.09
    咳咳
    -1.05
    喏
    -1.02
    多谢
    -1.01
    这是什么
    -0.93
    唉
    -0.90
    甭
    -0.89
     braccia
    -0.84
    POSITIVE LOGITS
    他和
    1.14
    他能
    1.10
    他对
    1.05
    眼前的
    0.98
     AÑOS
    0.97
    他知道
    0.97
    他不
    0.96
    他要
    0.94
    他没有
    0.94
     thier
    0.94
    Activations Density 3.143%

    No Known Activations