© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65119
    Prev
    Next
    INDEX
    Explanations

    android ViewModel imports

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

    This neuron fires on programming–style identifiers and import names—especially Android/Java API class names (e.g. androidx, ViewModel, Fragment, Providers) in code.

    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
    ).—
    -0.84
    写的
    -0.78
    tigem
    -0.77
     versucht
    -0.75
     naran
    -0.73
     paff
    -0.71
     använd
    -0.71
     taler
    -0.70
     Hinds
    -0.69
     outdoors
    -0.69
    POSITIVE LOGITS
     activity
    1.06
     ViewModel
    0.98
     factory
    0.92
    ViewModel
    0.91
     hilt
    0.90
    activity
    0.90
     factorial
    0.84
    Vä
    0.83
     активности
    0.80
     android
    0.78
    Activations Density 0.004%

    No Known Activations