© 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. 65255
    Prev
    Next
    INDEX
    Explanations

    android width attributes

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

    The neuron fires on layout/style property names (e.g. CSS “margin” and “padding” or XML “layout_width”).

    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
     also
    -1.53
    を
    -1.27
    それを
    -1.21
    それに
    -1.13
    そして
    -1.13
    と
    -1.12
    齟
    -1.01
     даже
    -1.00
    は
    -1.00
     octavo
    -0.99
    POSITIVE LOGITS
    沨
    1.30
     moverse
    1.22
    ままで
    1.20
    interrup
    1.17
     mostrarse
    1.17
     soñar
    1.16
     soltar
    1.15
     emplear
    1.14
    ものです
    1.13
     pelear
    1.13
    Activations Density 0.013%

    No Known Activations