© 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. 15643
    Prev
    Next
    INDEX
    Explanations

    separating list items or clauses

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

    The neuron fires on numeric tokens (especially numbers, including decimals).

    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
    неоп
    0.86
     fêtes
    0.86
     కార్య
    0.86
    倡
    0.83
    темати
    0.82
     successivement
    0.82
     obsług
    0.81
     acoustics
    0.81
     activités
    0.80
     gestão
    0.80
    POSITIVE LOGITS
    d
    0.94
    ed
    0.84
    en
    0.83
    b
    0.73
    est
    0.73
    …”
    0.71
    r
    0.71
    .”
    0.70
    n
    0.70
    ال
    0.69
    Activations Density 0.000%

    No Known Activations