© 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. 22-GEMMASCOPE-RES-131K
    7. 64981
    Prev
    Next
    INDEX
    Explanations

    phrase or punctuation

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

    This neuron detects code tokens specific to the Android Espresso UI‐testing API (e.g. onView, ViewMatchers, ViewActions, click).

    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
    kontroll
    -1.27
    panzer
    -1.23
     nyeri
    -1.16
    我
    -1.10
    akhir
    -1.09
    他
    -1.09
    landen
    -1.08
    她
    -1.06
    Τα
    -1.04
     seems
    -1.03
    POSITIVE LOGITS
    見ると
    1.23
    AdapterView
    1.21
     entlang
    1.18
    甚至是
    1.09
    又要
    1.08
    sian
    1.08
    フラー
    1.07
    と同
    1.06
    回了
    1.06
    вър
    1.06
    Activations Density 0.004%

    No Known Activations