© 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. 83607
    Prev
    Next
    INDEX
    Explanations

    package name

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

    This neuron fires on fully qualified package or import path tokens in code (e.g. “com.foo.bar” components).

    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
     э
    -0.88
    номи
    -0.88
    ทอง
    -0.85
    螯
    -0.83
     mə
    -0.80
    ƙ
    -0.76
    astic
    -0.76
     nagu
    -0.75
    اً
    -0.75
     attach
    -0.74
    POSITIVE LOGITS
    subpackage
    1.19
    ᛚ
    0.88
    Pack
    0.82
    cemment
    0.81
    gog
    0.81
     hike
    0.80
     soprano
    0.78
    čių
    0.78
    atimes
    0.77
    Manif
    0.76
    Activations Density 0.058%

    No Known Activations