© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3614
    Prev
    Next
    INDEX
    Explanations

    minecraft commands

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

    The neuron fires on tokens that appear in Java package/import declarations (especially in modded-Minecraft paths like “net.minecraft…”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Bandit
    -0.91
    iarkan
    -0.88
    _${
    -0.88
    Gud
    -0.87
    ukul
    -0.85
    导致
    -0.81
     domésticos
    -0.80
    platos
    -0.79
     tersangka
    -0.77
     mengapa
    -0.77
    POSITIVE LOGITS
     roten
    0.90
    Wel
    0.89
    till
    0.84
     STATISTICS
    0.83
     среднего
    0.83
    тения
    0.82
     причины
    0.81
    vantaged
    0.81
     world
    0.81
    BeforeEach
    0.81
    Activations Density 0.004%

    No Known Activations