© 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. 59277
    Prev
    Next
    INDEX
    Explanations

    România, dates, names

    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
    راک
    -0.80
     infest
    -0.75
     graphite
    -0.75
     illust
    -0.74
     stř
    -0.74
     sensors
    -0.73
     turbine
    -0.72
    传感器
    -0.72
     انداز
    -0.72
     Methane
    -0.71
    POSITIVE LOGITS
     tôi
    0.79
    currently
    0.78
    ึ
    0.72
    Estadio
    0.71
    сної
    0.71
    VARS
    0.71
    塙
    0.71
     rinsing
    0.70
    Selamat
    0.70
     kini
    0.70
    Activations Density 0.013%

    No Known Activations