© 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. 10-GEMMASCOPE-RES-131K
    7. 98917
    Prev
    Next
    INDEX
    Explanations

    increasing quantity or duration

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

    The neuron strongly activates on quantitative or comparative language—numbers, measurements, and words signaling increase or growth.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     now
    -1.77
     była
    -1.48
     first
    -1.45
     zapato
    -1.44
     reason
    -1.43
     family
    -1.41
     but
    -1.41
     organizar
    -1.41
     сегодня
    -1.36
     этого
    -1.34
    POSITIVE LOGITS
     possibilité
    1.37
     chanteur
    1.28
     możliwość
    1.26
     génie
    1.25
    öglich
    1.23
     GRATU
    1.23
     lagar
    1.19
    декват
    1.19
    踯
    1.17
     песню
    1.16
    Activations Density 0.053%

    No Known Activations