© 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. 22-GEMMASCOPE-RES-131K
    7. 35944
    Prev
    Next
    INDEX
    Explanations

    population statistics

    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_22/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
     then
    -1.39
     Primeiro
    -1.20
     Producción
    -1.18
     Início
    -1.11
     Mentre
    -1.06
    OWA
    -1.05
     Autó
    -1.05
     Automó
    -1.04
    ową
    -1.03
     Melhor
    -1.03
    POSITIVE LOGITS
     has
    1.52
     is
    1.45
    创建时间
    1.05
     on
    1.04
     it
    1.02
     was
    1.02
    It
    1.01
    INTRODUCCIÓN
    1.00
    ᐛ
    0.95
    这两个
    0.94
    Activations Density 0.103%

    No Known Activations