© 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. 10870
    Prev
    Next
    INDEX
    Explanations

    units of time

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

    The neuron fires on mentions of time spans (e.g. “years,” “minutes”)—i.e. expressions of duration.

    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
    जिक
    0.65
     approximately
    0.61
     approx
    0.61
    +.
    0.60
     Approximately
    0.60
     धमाकेदार
    0.60
     (+
    0.59
    approximately
    0.59
     ish
    0.58
     period
    0.57
    POSITIVE LOGITS
     nombreuses
    0.61
     متعدد
    0.61
    
    0.57
    ide
    0.56
    사람
    0.56
     pocas
    0.55
    grasp
    0.55
    RAT
    0.54
    INSTDIR
    0.54
     wenigen
    0.54
    Activations Density 0.127%

    No Known Activations