© 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. 98144
    Prev
    Next
    INDEX
    Explanations

    conditional code constructs

    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
     Nedir
    -1.74
    為に
    -1.71
    久し
    -1.69
    ційний
    -1.64
    Föld
    -1.60
    ところに
    -1.49
     női
    -1.47
    venez
    -1.47
     flera
    -1.46
    militar
    -1.46
    POSITIVE LOGITS
    if
    2.83
    //
    2.16
    for
    1.74
    なので
    1.52
    を
    1.50
     if
    1.44
    が
    1.38
    int
    1.38
    そのため
    1.27
    try
    1.26
    Activations Density 0.147%

    No Known Activations