© 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. 21649
    Prev
    Next
    INDEX
    Explanations

    sums and amounts

    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
     caneta
    -2.13
    笵
    -2.08
     pulseira
    -2.00
     almofada
    -2.00
     alça
    -1.95
     autres
    -1.86
     lâmpada
    -1.84
     geladeira
    -1.83
    ࿆
    -1.80
     câmera
    -1.79
    POSITIVE LOGITS
     Они
    2.14
    erráneo
    1.93
     to
    1.90
    tisgarh
    1.75
     lounging
    1.72
     When
    1.66
    никах
    1.66
     weshalb
    1.66
    S
    1.65
     nawet
    1.63
    Activations Density 0.006%

    No Known Activations