© 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. 30099
    Prev
    Next
    INDEX
    Explanations

    takes time and effort

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

    The neuron detects mentions of how long something takes, spotlighting verbs like “took” or “takes” that introduce time-duration phrases.

    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
    これは
    -1.05
     sny
    -0.96
     transmitter
    -0.87
     possibility
    -0.87
    Masukkan
    -0.86
     schen
    -0.85
    zmán
    -0.85
    úra
    -0.84
     Kanu
    -0.84
    kanen
    -0.84
    POSITIVE LOGITS
     longer
    1.80
     awhile
    1.71
     years
    1.38
    longer
    1.27
    Longer
    1.20
     months
    1.17
     about
    1.13
     us
    1.11
     them
    1.09
     effort
    1.09
    Activations Density 0.019%

    No Known Activations