© 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. 10-GEMMASCOPE-RES-131K
    7. 44061
    Prev
    Next
    INDEX
    Explanations

    Android UI setup and campaigns

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

    The neuron fires on Android layout resource references—especially numeric IDs passed to setContentView calls.

    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
     Setiap
    -2.27
     penjelasan
    -2.22
     Hingga
    -2.13
    A
    -2.06
     Ternyata
    -2.05
    🌟
    -2.05
     Bahkan
    -2.03
    ramienta
    -2.02
     Zweiten
    -2.02
     Kondisi
    -2.00
    POSITIVE LOGITS
                    
    2.14
    .
    2.06
     been
    2.06
                                
    2.02
                 
    2.02
                   
    1.98
                                   
    1.98
    狴
    1.98
     arranged
    1.98
    ll
    1.97
    Activations Density 0.000%

    No Known Activations