© 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. 22-GEMMASCOPE-RES-131K
    7. 73350
    Prev
    Next
    INDEX
    Explanations

    time durations

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

    The neuron fires on numeric expressions—numbers, measurements, time or quantity indicators, and other digit-based tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     in
    -1.50
     all
    -1.34
     from
    -1.30
     find
    -1.11
     many
    -1.09
     new
    -1.04
     Many
    -1.03
     found
    -1.02
    ovať
    -1.00
    gungen
    -1.00
    POSITIVE LOGITS
     duration
    2.03
     dauern
    1.47
     시간
    1.46
    duration
    1.44
     minutes
    1.39
     time
    1.35
     hour
    1.32
     время
    1.31
    时间
    1.27
     hours
    1.21
    Activations Density 0.033%

    No Known Activations