© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38375
    Prev
    Next
    INDEX
    Explanations

    code keywords and assignments

    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_22/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
     considerada
    -0.96
     görüntüleri
    -0.93
     так
    -0.93
     memberikan
    -0.92
    的一
    -0.91
    IRED
    -0.90
     typical
    -0.86
     desperdic
    -0.84
     alleged
    -0.84
     enemigo
    -0.82
    POSITIVE LOGITS
    Chaque
    0.97
    內容簡介
    0.94
    ]$}
    0.93
     ДЛЯ
    0.90
    Setiap
    0.90
    Каждый
    0.90
    Перевод
    0.89
    TextWatcher
    0.89
    的过程中
    0.88
    Dien
    0.88
    Activations Density 0.011%

    No Known Activations