© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16273
    Prev
    Next
    INDEX
    Explanations

    quitting or ending actions

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

    The neuron fires on interface navigation labels—words like “Settings,” “Options,” or “Preferences” that point to menu or configuration pages.

    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
     MLE
    0.64
     WUE
    0.63
     RMSE
    0.61
     LCA
    0.61
     September
    0.61
     T
    0.60
     Cavs
    0.60
     t
    0.59
     hapless
    0.59
     Qualifier
    0.59
    POSITIVE LOGITS
    墺
    0.55
    ADDING
    0.54
    deeds
    0.53
    manu
    0.53
    Ⲏ
    0.52
    部の
    0.52
     rendszer
    0.52
    akun
    0.52
     என்னும்
    0.51
    を通じて
    0.51
    Activations Density 0.001%

    No Known Activations