© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6336
    Prev
    Next
    INDEX
    Explanations

    modal followed by form or backdrop or script

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

    The neuron detects mentions of “modal” UI components in file paths or template names (e.g. modal-popup, modal-slide, modal-custom).

    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_31_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
     Settlement
    0.64
     Spacer
    0.64
     Detected
    0.55
     JTextField
    0.55
    롯
    0.55
     নিষ্প
    0.54
     Detector
    0.54
     வடக்கு
    0.54
     Charged
    0.52
    anwhile
    0.52
    POSITIVE LOGITS
    fin
    0.54
    COUNTRY
    0.54
    bd
    0.53
     anyways
    0.53
     shells
    0.52
    🤷
    0.52
    mités
    0.52
     sho
    0.51
     yog
    0.51
     lakes
    0.51
    Activations Density 0.000%

    No Known Activations