© 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. 23706
    Prev
    Next
    INDEX
    Explanations

    setting properties or values

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on mentions of the Qt “comboBox” widget (e.g. QComboBox) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    それぞれ
    -0.76
     círculo
    -0.75
    PKCS
    -0.73
     тенден
    -0.67
    Referencie
    -0.66
    oplus
    -0.65
    çalves
    -0.64
    =”
    -0.63
     havent
    -0.63
    二维
    -0.63
    POSITIVE LOGITS
     set
    1.05
    resize
    0.89
     Sandoval
    0.88
    set
    0.87
    hide
    0.86
     resize
    0.85
    classifiers
    0.80
     WORD
    0.77
    GEO
    0.77
     Malone
    0.77
    Activations Density 0.007%

    No Known Activations