© 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. 22-GEMMASCOPE-RES-131K
    7. 14016
    Prev
    Next
    INDEX
    Explanations

    programming constructs and UI elements

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

    The neuron fires on Android intent-launch calls—specifically patterns like “startActivityForResult” (and related chooser/request tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     markt
    -1.18
     straff
    -1.10
     garcía
    -1.05
    💯
    -1.04
     getMin
    -1.03
    ⃣
    -1.02
     Armee
    -1.02
     cikk
    -1.01
     felb
    -1.00
     支持
    -0.98
    POSITIVE LOGITS
     it
    1.54
     Notwendigkeit
    1.13
     this
    1.10
    fficients
    1.07
     opti
    1.06
     Fähigkeit
    1.05
     outrage
    1.05
    你说
    1.02
     unangemess
    1.02
     you
    1.02
    Activations Density 0.001%

    No Known Activations