© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62462
    Prev
    Next
    INDEX
    Explanations

    time durations since an event

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

    The neuron strongly activates on mentions of time spans expressed in “years” (especially when following a number).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Gör
    -0.87
    等は
    -0.85
    糜
    -0.81
    はこんな感じ
    -0.81
     thắng
    -0.79
    background
    -0.79
    Cada
    -0.78
    音が
    -0.78
    GridView
    -0.77
    sobre
    -0.77
    POSITIVE LOGITS
     since
    2.06
     depuis
    1.33
    Since
    1.30
    since
    1.29
     desde
    1.28
     Since
    1.26
     removed
    1.18
     منذ
    1.15
     after
    1.15
     nachdem
    1.05
    Activations Density 0.026%

    No Known Activations