© 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. 21354
    Prev
    Next
    INDEX
    Explanations

    opening bracket immediately after certain token

    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
    퐸
    -1.84
    ↵↵
    -1.66
    アクセサリー
    -1.65
     specifically
    -1.59
    ICIOS
    -1.58
     encompass
    -1.56
    ymm
    -1.55
    B
    -1.54
     either
    -1.47
     even
    -1.45
    POSITIVE LOGITS
    –
    1.90
    薮
    1.85
    الحياه
    1.84
     hij
    1.80
    梶
    1.77
     ]
    1.77
    枇
    1.74
     It
    1.73
    maxn
    1.73
     diego
    1.71
    Activations Density 0.004%

    No Known Activations