© 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. 55621
    Prev
    Next
    INDEX
    Explanations

    Java GUI programming

    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
    QPushButton
    -0.86
    ederen
    -0.82
    EndGlobal
    -0.79
    wort
    -0.76
    widgets
    -0.76
    ulario
    -0.75
    toggleClass
    -0.74
     noon
    -0.73
    =_
    -0.73
    ответ
    -0.73
    POSITIVE LOGITS
    jTable
    1.07
     j
    0.84
    dispose
    0.79
    Table
    0.78
    Default
    0.74
     Lazar
    0.74
     table
    0.73
     следующее
    0.73
     javax
    0.73
     الجد
    0.73
    Activations Density 0.002%

    No Known Activations