© 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. 33272
    Prev
    Next
    INDEX
    Explanations

    android, acronyms, or code snippets

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

    This neuron fires primarily on the Android XML namespace prefix (the “android” token in layout/attribute names).

    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
     it
    -1.31
    =>$
    -1.08
     and
    -1.05
    ごとの
    -0.97
    ناق
    -0.89
     before
    -0.88
    numberOf
    -0.86
     this
    -0.86
     what
    -0.85
    を行い
    -0.84
    POSITIVE LOGITS
    YSTAL
    1.12
     mivel
    0.98
     telefonu
    0.98
    CHELL
    0.97
     ので
    0.94
    虽说
    0.94
    dafx
    0.89
    inou
    0.89
    èmes
    0.89
    után
    0.87
    Activations Density 0.025%

    No Known Activations