© 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. 39364
    Prev
    Next
    INDEX
    Explanations

    going or being taken away

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.80
    迨
    -1.78
     矢量
    -1.77
    我这
    -1.71
     教程
    -1.70
     案例
    -1.65
    ?"
    -1.64
    睥
    -1.63
    ↵↵↵↵↵↵↵↵↵↵
    -1.62
    挹
    -1.62
    POSITIVE LOGITS
     Away
    2.03
    away
    1.93
    n
    1.88
    “
    1.88
    и
    1.85
    k
    1.74
    Away
    1.71
    ?
    1.70
     away
    1.68
    if
    1.66
    Activations Density 0.012%

    No Known Activations