© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128969
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens that name library or framework namespaces in import/using statements (e.g. “javax.json”, “Windows.UI.Xaml”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    section headers or common starters

    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_22/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
    ">',
    -0.88
     casi
    -0.86
     onData
    -0.84
     enfrenta
    -0.84
     AFTER
    -0.83
     fortsetter
    -0.83
    ][$
    -0.82
    ='%
    -0.81
     Mea
    -0.81
    salomon
    -0.80
    POSITIVE LOGITS
    établissement
    1.01
    ₰
    0.97
     ballerina
    0.95
     coordonnées
    0.93
     Liechtenstein
    0.93
     mantenga
    0.93
     ս
    0.91
    Kenmerken
    0.91
     Fg
    0.90
     combusti
    0.89
    Activations Density 0.000%

    No Known Activations