© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116648
    Prev
    Next
    INDEX
    Explanations

    Android Room, ViewModel, password recovery, Google Assistant

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

    This neuron fires on code snippets defining database models—especially Android Room entities and their related annotations.

    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
    acte
    -0.79
     Rossa
    -0.75
    幄
    -0.71
    Buckets
    -0.69
    tation
    -0.69
    nals
    -0.69
    >"+
    -0.69
     sist
    -0.68
    ocused
    -0.68
     Chatterjee
    -0.68
    POSITIVE LOGITS
     Room
    1.20
    Room
    1.19
     room
    1.16
    AsyncTask
    1.15
    room
    1.14
    ROOM
    1.12
    CrossRef
    0.96
     ROOM
    0.95
    Dao
    0.91
     Dao
    0.90
    Activations Density 0.007%

    No Known Activations