© 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. 16363
    Prev
    Next
    INDEX
    Explanations

    continue owning what you have

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

    This neuron fires on the main factual or “content” tokens in a sentence—especially numeric values, key action verbs, and named entities.

    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
     teknoloj
    0.74
    trying
    0.70
     politici
    0.69
     নিজেরাই
    0.69
     často
    0.68
     često
    0.68
    每天
    0.68
     அடிக்கடி
    0.68
     உருவாக்கி
    0.67
     다양
    0.65
    POSITIVE LOGITS
     reinstated
    1.09
     reinstatement
    1.04
     unharmed
    1.01
     kembali
    0.93
     regained
    0.92
     regain
    0.91
     rightful
    0.90
     forthwith
    0.90
     remanded
    0.88
     reinstate
    0.87
    Activations Density 0.635%

    No Known Activations