© 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. 5820
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly sensitive to standalone numeric tokens (e.g. years, page or figure numbers, decimal values) in the text.

    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
    นี้
    0.85
     ini
    0.80
    togel
    0.80
     αυτό
    0.76
     آسی
    0.73
    ค
    0.73
    轆
    0.73
     Pirates
    0.71
    魟
    0.71
    knn
    0.69
    POSITIVE LOGITS
    畄
    0.79
     uter
    0.74
     fuelwood
    0.74
     unge
    0.73
    㫜
    0.72
     Radiat
    0.71
    ++',
    0.71
     scegliere
    0.69
    <0x0B>
    0.68
     sylvis
    0.68
    Activations Density 0.001%

    No Known Activations