© 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. 97804
    Prev
    Next
    INDEX
    Explanations

    Qt GUI widgets and hierarchy

    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
    धे
    -0.89
    discuss
    -0.86
     Filipina
    -0.81
     unchanging
    -0.78
    灘
    -0.75
    ляется
    -0.75
    けます
    -0.75
     indeterminate
    -0.74
    副本
    -0.74
     hoody
    -0.71
    POSITIVE LOGITS
     parent
    1.52
    parent
    1.38
    Parent
    1.25
     parents
    1.12
     PARENT
    1.07
     Parent
    1.03
     QWidget
    1.02
    parents
    0.99
    getParent
    0.91
    Parenting
    0.90
    Activations Density 0.009%

    No Known Activations