© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119854
    Prev
    Next
    INDEX
    Explanations

    number sequences including '151'

    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
    In
    -3.03
    ]
    -2.45
     a
    -2.27
     senza
    -2.19
    On
    -1.99
    基本上
    -1.98
    ?
    -1.92
    t
    -1.90
    4
    -1.89
    很
    -1.88
    POSITIVE LOGITS
    кономі
    2.11
    
    2.11
    ቷ
    1.99
    坐下
    1.85
    朥
    1.83
     sinyal
    1.77
    馱
    1.76
    زارش
    1.75
    沄
    1.73
     Cancelar
    1.73
    Activations Density 0.021%

    No Known Activations