© 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. 31-GEMMASCOPE-2-RES-16K
    7. 629
    Prev
    Next
    INDEX
    Explanations

    date and number

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

    The neuron activates on standalone numeric tokens (especially floating‐point or date/time values).

    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_31_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
    0.71
     năm
    0.54
    ปี
    0.53
    google
    0.52
    year
    0.51
    to
    0.49
    1
    0.48
    año
    0.48
    साल
    0.47
    2
    0.47
    POSITIVE LOGITS
     Blocking
    0.45
     thofe
    0.43
     crooked
    0.43
     siku
    0.43
     Tregs
    0.42
    िशनर
    0.42
     Affidavit
    0.42
     tirar
    0.41
     heutigen
    0.41
     steeped
    0.41
    Activations Density 0.157%

    No Known Activations