© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73348
    Prev
    Next
    INDEX
    Explanations

    android code snippets

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

    This neuron detects occurrences of the word “Android,” especially in code contexts (e.g., import or package 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_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
     conquête
    -2.66
    1
    -2.52
     enam
    -2.52
    c
    -2.45
    籥
    -2.44
    u
    -2.41
    i
    -2.41
     Of
    -2.39
    縢
    -2.36
     jarring
    -2.30
    POSITIVE LOGITS
     этом
    3.14
    狆
    2.83
    {
    2.77
     wszyst
    2.73
    .
    2.73
    翾
    2.48
     změ
    2.45
     öffentliche
    2.38
     rozwią
    2.38
     Belakang
    2.34
    Activations Density 0.027%

    No Known Activations