© 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. 101694
    Prev
    Next
    INDEX
    Explanations

    with a/an/the noun

    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
    Ꭶ
    -1.63
    cessed
    -1.61
    bestos
    -1.58
     uden
    -1.54
     褲
    -1.53
    untuk
    -1.48
    )
    
    
    -1.45
    蛧
    -1.45
    ьере
    -1.44
    lowing
    -1.40
    POSITIVE LOGITS
     a
    2.09
     tampaknya
    1.66
     some
    1.50
    可不是
    1.41
     either
    1.36
     are
    1.35
     greifen
    1.34
     weiße
    1.30
    adeira
    1.28
    年も
    1.27
    Activations Density 0.127%

    No Known Activations