© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8785
    Prev
    Next
    INDEX
    Explanations

    time duration or quantity

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

    This neuron detects numeric tokens appearing as the bounds of a range—especially the second number in time or quantity ranges (e.g. cooking/shipping durations).

    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
    Too
    0.76
    בו
    0.73
    ²+
    0.73
    êu
    0.68
    Ông
    0.66
    Datos
    0.65
    uuuu
    0.63
    ‑
    0.63
    ⓓ
    0.63
    ::::::::::::::::
    0.62
    POSITIVE LOGITS
     depending
    0.93
     dependiendo
    0.87
     dozen
    0.87
     talvez
    0.80
     Depending
    0.80
     arası
    0.77
     gerne
    0.76
     tergantung
    0.75
    depending
    0.75
     maybe
    0.74
    Activations Density 0.122%

    No Known Activations