© 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. 110968
    Prev
    Next
    INDEX
    Explanations

    Euclidean and Manhattan distance calculations

    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
     dimulai
    -0.81
    Gemeinde
    -0.75
     Portion
    -0.73
     أمريكي
    -0.72
     suje
    -0.71
     indem
    -0.71
     stammer
    -0.69
    Ứng
    -0.68
     Cune
    -0.68
     постра
    -0.67
    POSITIVE LOGITS
     Euclidean
    1.98
     sqrt
    1.88
    sqrt
    1.66
     distance
    1.65
     squared
    1.52
    Distance
    1.47
     Distance
    1.46
    Sqrt
    1.44
     euc
    1.42
    distance
    1.41
    Activations Density 0.026%

    No Known Activations