© 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. 94109
    Prev
    Next
    INDEX
    Explanations

    JavaFX pane layout properties

    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
     window
    -0.85
    难
    -0.79
    říve
    -0.78
    QtCore
    -0.76
    ertes
    -0.75
     تغي
    -0.73
     PopupWindow
    -0.72
    entrée
    -0.71
    estors
    -0.71
    gemeinden
    -0.70
    POSITIVE LOGITS
     pref
    1.13
     children
    0.92
    getChildren
    0.90
    pref
    0.89
     alignment
    0.85
    Pref
    0.85
     Gap
    0.85
     Alignment
    0.85
    alignment
    0.82
    PROTOBUF
    0.81
    Activations Density 0.009%

    No Known Activations