© 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. 75068
    Prev
    Next
    INDEX
    Explanations

    drawing attention

    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
    ;
    
    -1.43
    They
    -1.41
    这样的
    -1.35
     تمامی
    -1.33
     favoris
    -1.29
     assise
    -1.29
    ↵
    -1.28
     ۳۰
    -1.28
     أو
    -1.27
    {
    
    -1.26
    POSITIVE LOGITS
     if
    1.66
    r
    1.53
     in
    1.52
     '
    1.42
    d
    1.40
    </strong>
    1.38
    くんの
    1.38
     because
    1.37
     Büro
    1.36
    
    1.36
    Activations Density 0.031%

    No Known Activations