© 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. 7614
    Prev
    Next
    INDEX
    Explanations

    September 2021 knowledge cutoff

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

    The neuron activates on numeric tokens (e.g. years, volume/page numbers, decimal values) in reference and citation entries.

    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
    Dieses
    0.82
    Р
    0.81
    В
    0.78
    Когда
    0.76
    Mientras
    0.76
    У
    0.75
    icient
    0.73
    Cuando
    0.73
     갖
    0.73
    П
    0.73
    POSITIVE LOGITS
     Summers
    0.87
    型的
    0.85
     boleh
    0.84
     alamat
    0.82
    धानिक
    0.81
    শিষ্ট
    0.80
     suitors
    0.80
     kuda
    0.80
     Chihuahua
    0.80
     maksimum
    0.80
    Activations Density 0.003%

    No Known Activations