© 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. 84563
    Prev
    Next
    INDEX
    Explanations

    javax java apis

    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
    jws
    -1.03
     aasta
    -1.00
     anymore
    -0.95
    態度
    -0.89
    fır
    -0.86
    结语
    -0.85
     tentativa
    -0.84
     to
    -0.83
     five
    -0.82
     cơn
    -0.82
    POSITIVE LOGITS
    swing
    1.51
     javax
    1.20
     Swing
    1.10
    javax
    1.06
    Swing
    1.03
     swing
    0.95
     klin
    0.95
     SUN
    0.87
     JFrame
    0.85
     soorten
    0.84
    Activations Density 0.001%

    No Known Activations