© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90865
    Prev
    Next
    INDEX
    Explanations

    multilingual comparisons

    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
    either
    -1.09
     either
    -0.98
    Either
    -0.93
    ствен
    -0.92
    вшие
    -0.91
    types
    -0.88
     loh
    -0.87
     kuni
    -0.85
     sowohl
    -0.85
     ihan
    -0.84
    POSITIVE LOGITS
     ever
    0.97
     akin
    0.95
     like
    0.94
    就像
    0.90
     much
    0.88
     starting
    0.85
     Starting
    0.85
    ฝ
    0.83
     sprzed
    0.82
     comparable
    0.81
    Activations Density 0.004%

    No Known Activations