© 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. 739
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on key content nouns—important topic words that signal what the text is about.

    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
     tempting
    0.55
     лише
    0.55
     (
    0.53
    ($"{
    0.53
     (~
    0.52
    其
    0.52
     jika
    0.50
     &/
    0.50
     (\"
    0.49
     ("
    0.48
    POSITIVE LOGITS
     ähm
    0.89
     그다음에
    0.84
     굉장히
    0.83
     everybody
    0.80
    Everybody
    0.77
    いろんな
    0.74
     bisschen
    0.73
     немно
    0.73
     Everybody
    0.72
     veldig
    0.72
    Activations Density 0.000%

    No Known Activations