© 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. 368
    Prev
    Next
    INDEX
    Explanations

    neonatal outcomes or cmath

    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
    k
    -2.67
    1
    -2.55
    Just
    -2.44
    可以说是
    -2.41
    ations
    -2.36
    需要
    -2.36
    All
    -2.30
    section
    -2.30
    ﮨ
    -2.27
    Such
    -2.23
    POSITIVE LOGITS
    ly
    3.34
     інших
    3.16
    褙
    2.56
     andere
    2.55
     outros
    2.48
     otros
    2.39
    ']
    
    2.38
    仃
    2.36
     of
    2.34
    .}
    2.30
    Activations Density 0.007%

    No Known Activations