© 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. 73438
    Prev
    Next
    INDEX
    Explanations

    Indonesia, Java, Workers, Chamber, fried noodles

    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
     Emmer
    -0.80
    겐
    -0.79
     Gek
    -0.78
     pers
    -0.77
     platt
    -0.74
     diciendo
    -0.73
     dang
    -0.72
    noticed
    -0.71
     집
    -0.71
     initData
    -0.71
    POSITIVE LOGITS
     사람
    0.87
     Schichten
    0.74
     夏
    0.74
    ⚂
    0.73
    男主
    0.72
    デモ
    0.71
     nhắn
    0.71
     informace
    0.71
    こうした
    0.71
    ✾
    0.71
    Activations Density 0.013%

    No Known Activations