© 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. 7048
    Prev
    Next
    INDEX
    Explanations

    merchant account and company

    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
     yearn
    -0.85
    榫
    -0.83
     monumental
    -0.81
    ギュラー
    -0.80
    叻
    -0.79
     pittore
    -0.78
    痪
    -0.76
     पहु
    -0.75
     enraged
    -0.75
     atingir
    -0.75
    POSITIVE LOGITS
    queryInterface
    0.95
    alism
    0.90
    ую
    0.83
    NÍ
    0.82
    âneo
    0.80
    udessa
    0.80
     Daniele
    0.80
     vessel
    0.79
    taire
    0.78
    vill
    0.78
    Activations Density 0.027%

    No Known Activations