© 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. 99174
    Prev
    Next
    INDEX
    Explanations

    startActivity Intent createChooser

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

    This neuron specializes in spotting Android-specific coding terms—especially Intent/Activity navigation keywords and flag constants.

    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
    sus
    -0.79
    TokenNameRPAREN
    -0.73
    𝗇
    -0.71
     ruas
    -0.68
    duos
    -0.68
     thiên
    -0.68
    alti
    -0.68
    tský
    -0.67
     Пред
    -0.67
    rodu
    -0.66
    POSITIVE LOGITS
     Intent
    2.20
     intent
    2.16
    Intent
    2.05
    intent
    1.77
    startActivity
    1.42
     intention
    1.36
     intents
    1.34
    PendingIntent
    1.29
     intentions
    1.29
    意
    1.17
    Activations Density 0.052%

    No Known Activations