© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113752
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives after an article

    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
    0
    -2.06
     this
    -1.84
     it
    -1.83
    了一個
    -1.67
     in
    -1.67
     until
    -1.56
    却被
    -1.56
     for
    -1.55
     if
    -1.55
     during
    -1.53
    POSITIVE LOGITS
    內容簡介
    1.88
     dün
    1.77
     firſt
    1.53
    karakter
    1.53
     parfü
    1.51
    :「
    1.50
    ♾
    1.46
    ⦁
    1.45
     minimalista
    1.44
    struktur
    1.43
    Activations Density 0.054%

    No Known Activations