© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112282
    Prev
    Next
    INDEX
    Explanations

    UI elements and actions

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

    Looking at the activations, this neuron strongly activates on words that appear in user interface contexts, particularly: - UI action words like "menu item with", "page", "message in", "Image", "File and", "Window and", "Save As", "Find Next",

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    荨
    -1.33
    在那
    -1.30
     conducteur
    -1.27
    ombus
    -1.26
     ESPEC
    -1.25
    follows
    -1.25
     <>",
    -1.25
     enthou
    -1.24
    isait
    -1.21
    anasia
    -1.20
    POSITIVE LOGITS
     like
    1.63
     about
    1.48
     by
    1.29
     nemico
    1.25
     greater
    1.25
    無し
    1.23
     without
    1.23
     albero
    1.20
     well
    1.19
     paziente
    1.17
    Activations Density 0.112%

    No Known Activations