© 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. 102428
    Prev
    Next
    INDEX
    Explanations

    catalogue or catalog listings

    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
    鹛
    -2.45
    
    -2.28
    桫
    -2.08
     philosop
    -1.99
    妧
    -1.90
    炱
    -1.88
    铪
    -1.80
    烺
    -1.80
    gibt
    -1.80
    Москва
    -1.78
    POSITIVE LOGITS
    ]
    2.47
    —
    2.28
    in
    2.17
     siap
    2.13
     страницы
    1.99
     increasingly
    1.98
    '
    1.97
    頑張
    1.93
     продукции
    1.88
    In
    1.88
    Activations Density 0.007%

    No Known Activations