© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103193
    Prev
    Next
    INDEX
    Explanations

    years of activity or existence

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

    The neuron activates on time‐duration phrases of the form “[number][unit] of …,” e.g. “years of raising,” “months of waiting,” “weeks of training,” etc.

    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
    ensitive
    -1.13
     cyclisme
    -1.10
    oluble
    -1.09
     tijden
    -1.08
     recente
    -1.06
    了过来
    -1.05
     imposible
    -1.04
     celé
    -1.03
    recently
    -1.03
    termilk
    -1.03
    POSITIVE LOGITS
     existence
    1.41
     intense
    1.38
     being
    1.38
     intensive
    1.17
     continuous
    1.13
     exposure
    1.13
     существо
    1.10
     помню
    1.07
     effort
    1.06
     using
    1.05
    Activations Density 0.048%

    No Known Activations