© 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. 23720
    Prev
    Next
    INDEX
    Explanations

    programming code and technical terms

    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
    olle
    -0.85
     İş
    -0.82
    clearfix
    -0.82
    easier
    -0.82
     tider
    -0.81
     ordf
    -0.80
    lua
    -0.78
    ってきた
    -0.77
     nemlig
    -0.77
    kapat
    -0.76
    POSITIVE LOGITS
    if
    1.19
    global
    1.00
     globally
    0.89
    window
    0.88
     however
    0.87
     глоба
    0.84
    document
    0.82
     global
    0.82
    console
    0.82
    unen
    0.81
    Activations Density 0.011%

    No Known Activations