© 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. 72302
    Prev
    Next
    INDEX
    Explanations

    military and naval actions historical

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

    The main thing this neuron does is detect numeric information—quantities, dates, measurements, and other number tokens.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Chaque
    -1.56
     fredag
    -1.42
    mereka
    -1.40
     naše
    -1.39
     here
    -1.38
    ffekt
    -1.36
     miljö
    -1.35
    ícia
    -1.34
     onsdag
    -1.32
    ável
    -1.31
    POSITIVE LOGITS
     حتی
    1.70
     despite
    1.66
     даже
    1.62
     even
    1.57
     Despite
    1.51
    Despite
    1.48
    Even
    1.47
     fourteen
    1.41
     sogar
    1.40
     навіть
    1.37
    Activations Density 0.260%

    No Known Activations