© 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. 102437
    Prev
    Next
    INDEX
    Explanations

    days, hours, years

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

    This neuron responds to mentions of time‐interval units (e.g. “days,” “months,” “hours”).

    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
    泚
    -1.77
    ﹞
    -1.63
    DNEY
    -1.56
    禤
    -1.55
    取决
    -1.55
     của
    -1.50
    趄
    -1.50
    憍
    -1.50
    鑁
    -1.50
    さあ
    -1.48
    POSITIVE LOGITS
    -
    2.22
    In
    2.00
    2
    1.85
    my
    1.81
     $
    1.77
    ’
    1.76
    "
    1.76
    e
    1.70
    in
    1.69
    (),
    1.64
    Activations Density 0.014%

    No Known Activations