© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12380
    Prev
    Next
    INDEX
    Explanations

    time durations and quantities

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

    The neuron identifies numeric time and duration references (e.g. hours, minutes, days, dates, and specific clock times).

    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
     ago
    1.05
     बीत
    0.84
    以來
    0.80
     geleden
    0.80
     óta
    0.79
    以来
    0.79
     away
    0.74
     (>
    0.71
    Ago
    0.69
     elapse
    0.68
    POSITIVE LOGITS
     qualità
    0.56
     chiam
    0.55
     prendere
    0.55
     sezione
    0.52
     concetto
    0.52
    本次
    0.51
     linguaggio
    0.51
    чик
    0.51
     composé
    0.50
     tecniche
    0.50
    Activations Density 0.157%

    No Known Activations