© 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. 34-GEMMASCOPE-RES-131K
    7. 90018
    Prev
    Next
    INDEX
    Explanations

    array size or dimension

    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_34/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
    筍
    -0.80
    غب
    -0.78
    Cancelar
    -0.78
    ratio
    -0.77
    منة
    -0.76
     vitally
    -0.75
     eight
    -0.73
    ıştır
    -0.72
    ższe
    -0.72
     goes
    -0.71
    POSITIVE LOGITS
     size
    2.59
     Size
    1.99
    Size
    1.88
     dimension
    1.81
    size
    1.77
     length
    1.73
     размер
    1.56
     размера
    1.50
     SIZE
    1.47
     Dimension
    1.46
    Activations Density 0.041%

    No Known Activations