© 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. 58283
    Prev
    Next
    INDEX
    Explanations

    vertical orientation

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

    The neuron activates on UI layout component names and their attributes (e.g. Android/XML view tags, class names like “LinearLayout,” property names like “orientation,” 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
     quitté
    -0.82
     mutagenicity
    -0.78
    arduino
    -0.74
     precisar
    -0.73
    ﻀ
    -0.72
     večer
    -0.71
    وفي
    -0.71
    وفق
    -0.71
    Zambia
    -0.71
    tôi
    -0.69
    POSITIVE LOGITS
     orientation
    3.03
    orientation
    2.47
     Orientation
    2.38
    Orientation
    2.31
     orient
    2.27
     orientations
    2.13
     oriented
    2.02
     vertical
    1.98
    orient
    1.95
     ORIENT
    1.88
    Activations Density 0.035%

    No Known Activations