© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48948
    Prev
    Next
    INDEX
    Explanations

    curly braces around expressions

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

    This neuron flags string tokens that look like filesystem or URL path segments (e.g. "../", "/", and other path components) often in import/source declarations.

    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
    Château
    -0.81
    dames
    -0.81
    grafen
    -0.81
    Lorsque
    -0.80
    Див
    -0.79
     beleid
    -0.79
    Tum
    -0.75
    seleccion
    -0.75
    观看
    -0.74
    eventName
    -0.73
    POSITIVE LOGITS
    StatusBar
    1.10
     indicator
    1.05
    indicator
    0.91
    clientHeight
    0.89
     current
    0.89
     indicators
    0.88
     list
    0.87
    animation
    0.87
     animation
    0.86
     tab
    0.84
    Activations Density 0.008%

    No Known Activations