© 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. 34-GEMMASCOPE-RES-131K
    7. 31133
    Prev
    Next
    INDEX
    Explanations

    duration + subject + verb

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

    The neuron activates on expressions of temporal duration—phrases that specify how long something lasts or occurred.

    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
     sempre
    -1.03
     शुरू
    -1.01
    بدأ
    -0.96
    atecas
    -0.96
     momentarily
    -0.94
    永远
    -0.94
     zač
    -0.91
     πάντα
    -0.91
    开始
    -0.90
     شروع
    -0.90
    POSITIVE LOGITS
     remain
    1.52
     estuvo
    1.51
     stay
    1.44
     remained
    1.44
     existed
    1.24
     keep
    1.24
     maintained
    1.23
     kept
    1.23
    ままで
    1.16
     stayed
    1.16
    Activations Density 0.058%

    No Known Activations