© 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. 34-GEMMASCOPE-RES-131K
    7. 49768
    Prev
    Next
    INDEX
    Explanations

    clicking on icons or links

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

    The neuron detects user‐interface click instructions, especially the phrase “click on an icon below.”

    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
    clicked
    -0.88
    点击
    -0.84
    uko
    -0.82
     عبر
    -0.81
    told
    -0.80
    arching
    -0.80
    UKO
    -0.80
    putting
    -0.79
    ╝
    -0.77
    czenia
    -0.77
    POSITIVE LOGITS
     name
    1.41
     icon
    1.40
     icons
    1.21
     names
    1.15
     any
    1.14
    任意
    1.09
     title
    1.09
     highlighted
    1.08
     titles
    1.07
     anywhere
    1.06
    Activations Density 0.079%

    No Known Activations