© 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. 34-GEMMASCOPE-RES-131K
    7. 64055
    Prev
    Next
    INDEX
    Explanations

    android xml layout attributes

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

    The neuron flags numeric tokens (digits or numbers) in XML attribute values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     LIT
    -0.91
     trous
    -0.89
    Cel
    -0.86
    骡
    -0.81
    Conne
    -0.80
    LAN
    -0.79
    icanos
    -0.79
    LEI
    -0.78
     CIM
    -0.78
    搅
    -0.77
    POSITIVE LOGITS
     from
    1.04
     their
    0.97
    styleable
    0.94
     during
    0.93
     almost
    0.90
     both
    0.90
     other
    0.89
     many
    0.89
     those
    0.87
     directly
    0.87
    Activations Density 0.005%

    No Known Activations