© 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. 34870
    Prev
    Next
    INDEX
    Explanations

    time or date references

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

    The neuron fires on tokens that are primarily numeric or alphanumeric identifiers (e.g. version numbers, container IDs, timestamps).

    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
    Ḵ
    -0.85
     zunächst
    -0.82
    太多
    -0.82
     nightly
    -0.80
    年度
    -0.80
     existing
    -0.77
    Flickr
    -0.77
    reur
    -0.77
    ítu
    -0.76
    Câ
    -0.75
    POSITIVE LOGITS
     yesterday
    2.17
     ago
    2.17
     hours
    1.67
    ago
    1.66
    Yesterday
    1.65
     Yesterday
    1.62
    Ago
    1.59
    yesterday
    1.41
     minutes
    1.35
    Hace
    1.34
    Activations Density 0.070%

    No Known Activations