© 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. 22-GEMMASCOPE-RES-131K
    7. 16728
    Prev
    Next
    INDEX
    Explanations

    time units: minute, minutes

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

    The neuron flags occurrences of the word “minute” (in any capitalization or plural form), i.e. mentions of time intervals measured in minutes.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     beliebtesten
    -2.66
     Ejecutivo
    -2.47
     you
    -2.44
     Näch
    -2.42
     votación
    -2.38
     quando
    -2.38
     asamblea
    -2.34
    ,’
    -2.30
     streamlining
    -2.19
     REALLY
    -2.16
    POSITIVE LOGITS
    that
    2.72
    ᕱ
    2.47
    you
    2.42
    ᭝
    2.39
     appartement
    2.39
     higiene
    2.38
    ・・・」
    2.36
    噐
    2.34
    ～！
    2.30
          
    2.25
    Activations Density 0.014%

    No Known Activations