© 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. 93598
    Prev
    Next
    INDEX
    Explanations

    XML attributes and code

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

    This neuron picks out Android XML attribute values (e.g. booleans like true, enums like auto, layout size keywords such as match_parent or wrap_content, gravity and RTL settings, numeric dimensions, etc.).

    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
    ImageLoader
    -0.88
     murderer
    -0.82
    Jasmine
    -0.80
     habr
    -0.78
    )("
    -0.76
    enapa
    -0.75
    recorded
    -0.74
    ἔ
    -0.74
    etí
    -0.74
    ₘ
    -0.74
    POSITIVE LOGITS
    eniendo
    0.83
     currentValue
    0.81
     disponibile
    0.81
    梨
    0.80
    DHCP
    0.79
     trattano
    0.78
    None
    0.78
    none
    0.77
     ابتدا
    0.77
     none
    0.76
    Activations Density 0.003%

    No Known Activations