© 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. 65910
    Prev
    Next
    INDEX
    Explanations

    graphic followed by noun

    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
    {
    -2.86
    т
    -1.80
     paradig
    -1.72
    你有
    -1.66
                
    -1.66
     régiment
    -1.66
     was
    -1.63
    如图
    -1.61
    ت
    -1.59
          
    -1.56
    POSITIVE LOGITS
    褡
    1.98
     cuarent
    1.84
     objectMapper
    1.83
    इटम
    1.82
    頭に
    1.77
    vindo
    1.76
    Twenty
    1.75
    喊道
    1.73
    必要があります
    1.71
     nacht
    1.68
    Activations Density 0.005%

    No Known Activations