© 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. 8798
    Prev
    Next
    INDEX
    Explanations

    yes, ok, a

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

    This neuron fires on tokens that represent users’ selected prompt options or confirmation answers (e.g. “Yes,” “a,” “no”) in interactive dialogs.

    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
     toxins
    0.52
    በባ
    0.51
    their
    0.47
     বাঙ
    0.47
    முத
    0.47
     tripled
    0.46
    distributions
    0.46
    빻
    0.46
    stripos
    0.46
     pleasurable
    0.45
    POSITIVE LOGITS
     ampl
    0.50
     caso
    0.49
    になる
    0.47
     QTL
    0.46
     prevista
    0.45
     naman
    0.45
     contesto
    0.45
     –
    0.45
    ,
    0.45
     -
    0.45
    Activations Density 0.000%

    No Known Activations