© 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. 73571
    Prev
    Next
    INDEX
    Explanations

    UPI followed by parenthesis

    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
     cố
    -0.68
     write
    -0.68
    devs
    -0.66
    WRITE
    -0.65
    каде
    -0.65
     청
    -0.64
     آبی
    -0.62
    auteur
    -0.61
     ignore
    -0.60
    igny
    -0.60
    POSITIVE LOGITS
    روفایل
    0.78
     Алла
    0.75
    BACKEND
    0.72
    ortiment
    0.71
     betale
    0.71
    worden
    0.68
    Tup
    0.68
    mayan
    0.67
    ึกษา
    0.66
     lae
    0.66
    Activations Density 0.048%

    No Known Activations