© 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. 118121
    Prev
    Next
    INDEX
    Explanations

    tab navigation and focus control

    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
     turnout
    -0.77
     Jura
    -0.73
    さっぱり
    -0.72
    SizeMode
    -0.71
    lible
    -0.70
    ファイルを
    -0.70
    ële
    -0.69
    displaymath
    -0.67
     »,
    -0.67
     confidentiality
    -0.66
    POSITIVE LOGITS
     focus
    1.84
     tabindex
    1.79
     tab
    1.68
     TAB
    1.66
    Tab
    1.59
    TAB
    1.57
     Focus
    1.52
     Tab
    1.52
    focus
    1.51
    tab
    1.48
    Activations Density 0.054%

    No Known Activations