© 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. 109527
    Prev
    Next
    INDEX
    Explanations

    swift class definitions

    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
    sche
    -1.03
    )(
    -0.93
     jadx
    -0.88
    itattu
    -0.83
    ="$(
    -0.82
    '=>$
    -0.81
     blew
    -0.80
    ровке
    -0.79
     __(
    -0.78
    =(
    -0.77
    POSITIVE LOGITS
    :
    1.41
    ：……
    0.90
     argentino
    0.85
    让她
    0.85
     {
    0.83
     problemet
    0.81
    اري
    0.81
    联盟
    0.80
    🐏
    0.80
    渍
    0.79
    Activations Density 0.009%

    No Known Activations