© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15683
    Prev
    Next
    INDEX
    Explanations

    time units and durations

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

    The neuron mainly detects numeric expressions of time durations (e.g. “3 minutes,” “2 hours,” etc.).

    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
    +
    0.80
    ±
    0.68
     years
    0.67
    ≈
    0.64
    +-
    0.63
    ×
    0.61
    +.
    0.61
    %
    0.60
    -
    0.59
    +,
    0.59
    POSITIVE LOGITS
     asesor
    0.49
     områ
    0.47
     evitare
    0.47
     instalación
    0.46
     umfang
    0.46
     ausreiche
    0.45
    大規模
    0.44
    үнд
    0.44
    㙅
    0.44
    .';
    0.43
    Activations Density 0.129%

    No Known Activations