© 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. 10-GEMMASCOPE-RES-131K
    7. 130227
    Prev
    Next
    INDEX
    Explanations

    android app components

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

    The neuron fires on the “app” segment in import paths—i.e. it spots import statements that bring in classes from the android.app package.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     insanely
    -1.96
     continually
    -1.95
     wonderfully
    -1.95
     lauded
    -1.93
     unbelievably
    -1.92
     rapidamente
    -1.90
     alcuni
    -1.85
     exceptionally
    -1.84
     delightfully
    -1.84
     geralmente
    -1.83
    POSITIVE LOGITS
    Though
    2.33
    Although
    2.19
    Despite
    2.11
    Before
    2.06
    After
    2.02
    Unlike
    1.97
    Even
    1.95
    Like
    1.91
    Since
    1.91
    Both
    1.86
    Activations Density 0.005%

    No Known Activations