© 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. 10-GEMMASCOPE-RES-131K
    7. 11117
    Prev
    Next
    INDEX
    Explanations

    time ranges

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

    The neuron detects the “to” that links start and end times in time‐range expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     mentre
    -1.86
    recently
    -1.66
    
    -1.62
     kompati
    -1.57
     ſou
    -1.55
    躄
    -1.53
    ୬
    -1.53
    several
    -1.52
    up
    -1.52
    なども
    -1.51
    POSITIVE LOGITS
     These
    1.80
    ↵↵
    1.62
     This
    1.59
    </em>
    1.58
    توضیحات
    1.51
     Stadtteil
    1.51
     time
    1.50
     Unlike
    1.46
     Eigentum
    1.44
     IN
    1.43
    Activations Density 0.006%

    No Known Activations