© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60643
    Prev
    Next
    INDEX
    Explanations

    some time or duration

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

    This neuron activates on expressions of elapsed time or duration (e.g. “for some time,” specific month‐ or year‐counts), especially when a numeric span is given.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     some
    -1.30
     quelques
    -1.08
     alcuni
    -1.03
     nějak
    -1.02
     برخی
    -0.97
    ător
    -0.92
    شهاد
    -0.90
     некоторые
    -0.88
    āya
    -0.85
    atisk
    -0.85
    POSITIVE LOGITS
     months
    1.48
     years
    1.41
     dozen
    1.28
     aikaa
    1.17
     weeks
    1.06
     considerable
    1.06
     unspecified
    1.02
    while
    1.02
     distance
    1.02
     while
    0.98
    Activations Density 0.021%

    No Known Activations