© 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. 10-GEMMASCOPE-RES-131K
    4. 123732
    Prev
    Next
    INDEX
    Explanations

    mathematical addition operator appearances

    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_10/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
    </strong>
    -3.34
    is
    -2.55
    at
    -2.53
    .
    -2.39
    </h4>
    -2.22
    how
    -2.20
    for
    -2.19
     to
    -2.08
    m
    -2.08
    <strong>
    -2.06
    POSITIVE LOGITS
    ším
    2.56
    ୌ
    2.55
    呖
    2.52
     {
    
    2.47
     verir
    2.42
    他的
    2.38
    ⃢
    2.31
    苤
    2.31
     accustomed
    2.28
    螣
    2.25
    Activations Density 0.121%

    No Known Activations