© 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. 74408
    Prev
    Next
    INDEX
    Explanations

    years past a number

    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
    味付け
    -1.89
    奬
    -1.83
     Cæ
    -1.81
     to
    -1.66
     книг
    -1.61
    いしい
    -1.58
    これを
    -1.58
     современных
    -1.57
    应该
    -1.55
    чком
    -1.54
    POSITIVE LOGITS
    Моя
    2.09
     město
    1.99
    🩱
    1.98
    dây
    1.98
    𝒙
    1.97
    enschappen
    1.94
     Sabtu
    1.94
    Мой
    1.91
    ğim
    1.90
     April
    1.88
    Activations Density 0.159%

    No Known Activations