© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93700
    Prev
    Next
    INDEX
    Explanations

    headings and titles

    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
    ruckt
    -0.86
    addWidget
    -0.83
    ил
    -0.82
    QSize
    -0.81
    él
    -0.79
    可能
    -0.78
    JFrame
    -0.77
    お
    -0.77
    PopupWindow
    -0.77
    delete
    -0.76
    POSITIVE LOGITS
    的动作
    0.89
    sS
    0.87
     robar
    0.87
    兴奋
    0.86
     vêtements
    0.84
     habituellement
    0.82
    那么多
    0.82
    綺麗な
    0.82
    錆
    0.80
     considérable
    0.80
    Activations Density 0.000%

    No Known Activations