© 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. 34-GEMMASCOPE-RES-131K
    7. 106946
    Prev
    Next
    INDEX
    Explanations

    Android activities and imports

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

    The neuron activates on import statements in code, identifying the “import” keyword and its related package names.

    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
     competition
    -0.84
     Zachary
    -0.82
    endes
    -0.81
    anka
    -0.80
     OBITUARY
    -0.79
     granted
    -0.79
     ADHD
    -0.78
     TAMB
    -0.78
    view
    -0.76
    Zachary
    -0.76
    POSITIVE LOGITS
     androidx
    1.32
     support
    1.19
    support
    1.16
     MainActivity
    1.14
    SUPPORT
    1.10
    Support
    1.01
    Supporting
    0.96
     حمایت
    0.95
     mendukung
    0.94
    Supports
    0.94
    Activations Density 0.010%

    No Known Activations