© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31759
    Prev
    Next
    INDEX
    Explanations

    over the last/past

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

    The neuron detects expressions of elapsed time framing a period (e.g. "over the past …," "for … years").

    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
     a
    -1.23
     subsequent
    -0.93
     one
    -0.90
     an
    -0.89
     Übersetzungen
    -0.88
     Herausgeber
    -0.87
     centuries
    -0.86
     some
    -0.85
     उस
    -0.84
     занимает
    -0.84
    POSITIVE LOGITS
     the
    3.67
     afgelopen
    1.87
     последние
    1.82
    过去
    1.55
     letzten
    1.52
     últimos
    1.50
     last
    1.44
     posled
    1.41
     último
    1.39
     послед
    1.38
    Activations Density 0.105%

    No Known Activations