© 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. 10-GEMMASCOPE-RES-131K
    7. 74347
    Prev
    Next
    INDEX
    Explanations

    X rather than Y

    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
    じゃない
    -1.97
    )
    -1.94
     australiano
    -1.85
     cały
    -1.84
    ांकि
    -1.82
    ↵↵
    -1.81
    ふと
    -1.76
     requirement
    -1.75
     Bretaña
    -1.72
    裡
    -1.72
    POSITIVE LOGITS
     to
    2.08
    Ꮉ
    2.06
    which
    1.99
    го
    1.92
     have
    1.90
    鸲
    1.82
    Which
    1.81
    鍆
    1.81
    iters
    1.80
    n
    1.78
    Activations Density 0.006%

    No Known Activations