© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70290
    Prev
    Next
    INDEX
    Explanations

    programming language identifiers

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

    The neuron activates on the identifier “content” (e.g. in import or package declarations like android.content).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     "
    -1.99
     一
    -1.79
    4
    -1.79
    [
    -1.79
     =
    -1.77
     -
    -1.71
    了一
    -1.68
    te
    -1.68
    "
    -1.66
    ...
    -1.62
    POSITIVE LOGITS
     pintadas
    1.88
     plásticos
    1.87
     oxígeno
    1.85
     །
    1.80
    躥
    1.76
     Schriftsteller
    1.75
     azúcar
    1.74
    <bos>
    1.74
     ſet
    1.72
    柺
    1.72
    Activations Density 0.084%

    No Known Activations