© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3403
    Prev
    Next
    INDEX
    Explanations

    create, configure, or edit files

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

    This neuron activates on names of UI elements and navigation instructions (e.g. menu or button labels and related “click/select” directives) in technical documentation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    তরাং
    0.73
     ReturnVal
    0.71
     పరిస్థి
    0.66
    是以
    0.63
    性格
    0.62
     floribus
    0.62
     позволи
    0.61
     disintegration
    0.61
     परिवारों
    0.61
    olactone
    0.61
    POSITIVE LOGITS
     your
    0.90
     yourself
    0.88
     youre
    0.82
     configure
    0.82
     Configure
    0.80
    your
    0.79
     Edit
    0.79
     Notepad
    0.78
    あなたの
    0.77
     нажмите
    0.77
    Activations Density 0.012%

    No Known Activations