© 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. 30035
    Prev
    Next
    INDEX
    Explanations

    this year/season

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

    The neuron activates strongly on numerical data and quantitative measures (counts, points, percentages, etc.).

    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
    These
    -1.93
     Эти
    -1.63
    Эти
    -1.38
     takimi
    -1.34
    Yesterday
    -1.30
     continúas
    -1.27
    Today
    -1.27
     dichas
    -1.26
     Estos
    -1.24
    řízen
    -1.24
    POSITIVE LOGITS
     this
    11.13
    this
    5.25
     هذا
    5.03
     цього
    4.53
     этого
    4.47
     этом
    4.38
     этой
    4.13
    นี้
    3.91
     dieses
    3.89
     này
    3.84
    Activations Density 0.343%

    No Known Activations