© 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. 113388
    Prev
    Next
    INDEX
    Explanations

    Yun/Yoon names and places

    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
     zusätzlichen
    -3.20
    2
    -3.19
     nawet
    -3.02
    3
    -2.97
    絰
    -2.83
     Unterschiede
    -2.80
    ～　
    -2.80
    0
    -2.78
    ⽌
    -2.77
     individuellen
    -2.63
    POSITIVE LOGITS
    
    2.66
    ༷
    2.53
    鍇
    2.50
    ]
    2.50
    Ꮈ
    2.36
    芣
    2.36
    蚡
    2.31
     artificiales
    2.30
     suced
    2.28
     tecn
    2.25
    Activations Density 0.003%

    No Known Activations