© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2825
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to four-digit numeric tokens (often years or similar numbers with decimal points).

    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
    пли
    0.94
    ли
    0.88
    asi
    0.87
    リ
    0.79
    си
    0.78
    ла
    0.77
    ար
    0.75
    な
    0.75
    țiilor
    0.74
     patients
    0.73
    POSITIVE LOGITS
     выступ
    0.74
    }{
    0.73
    hedge
    0.72
    jButton
    0.71
     orbifold
    0.70
     وهذه
    0.69
    exhaustive
    0.69
     сотрудни
    0.69
     uphold
    0.68
     bylo
    0.68
    Activations Density 0.000%

    No Known Activations