© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14288
    Prev
    Next
    INDEX
    Explanations

    AI assistant refusal

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

    The main thing this neuron does is detect standalone numeric tokens (numbers).

    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
     ‫
    0.64
     
    0.62
     ma
    0.61
     Fossil
    0.59
     Pills
    0.57
     の
    0.55
     Promenade
    0.55
     fossil
    0.54
     بھی
    0.54
     Would
    0.54
    POSITIVE LOGITS
    Disclaimer
    0.75
    jekt
    0.69
     первое
    0.69
    NOTA
    0.66
    NOTE
    0.66
    сі
    0.66
    explanatory
    0.66
    ᱑
    0.64
    ankind
    0.64
    BEGIN
    0.64
    Activations Density 0.035%

    No Known Activations