© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1664
    Prev
    Next
    INDEX
    Explanations

    Spring Boot web context

    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
    وقف
    -1.02
    >):
    -0.96
    硯
    -0.96
    ឃ
    -0.94
    橡
    -0.93
    Sparta
    -0.90
     aDecoder
    -0.88
    Durant
    -0.88
     Polisi
    -0.88
    يز
    -0.88
    POSITIVE LOGITS
    boot
    1.09
    web
    1.02
    http
    1.00
     boot
    0.98
    util
    0.93
     kilomètres
    0.89
     operativo
    0.88
     botones
    0.88
    A
    0.88
     web
    0.86
    Activations Density 0.003%

    No Known Activations