© 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. 98052
    Prev
    Next
    INDEX
    Explanations

    sidebar widgets and navigation

    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
    遽
    -0.82
    タジー
    -0.77
    oges
    -0.76
    భ
    -0.74
    zęd
    -0.74
    eria
    -0.72
    Modifiers
    -0.72
    lasses
    -0.69
    vade
    -0.69
     żół
    -0.68
    POSITIVE LOGITS
     widget
    1.70
    Widget
    1.51
    widget
    1.47
     Widget
    1.46
     sidebar
    1.43
    sidebar
    1.41
     widgets
    1.33
     recent
    1.18
    Sidebar
    1.15
     Recent
    1.13
    Activations Density 0.028%

    No Known Activations