© 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. 85052
    Prev
    Next
    INDEX
    Explanations

    time periods

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

    The neuron is strongly activated by words denoting temporal units or periods (e.g. year, day, season, night).

    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
     and
    -1.68
    </i>
    -1.62
    </b>
    -1.35
     kwietnia
    -1.34
     who
    -1.33
     összefoglal
    -1.33
     início
    -1.25
     beginnen
    -1.24
    skilled
    -1.24
     on
    -1.23
    POSITIVE LOGITS
     we
    2.16
     were
    1.89
     there
    1.66
    Things
    1.48
    Trying
    1.39
    odils
    1.37
    鱟
    1.36
    .}(
    1.35
     it
    1.34
     they
    1.32
    Activations Density 0.079%

    No Known Activations