© 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. 68393
    Prev
    Next
    INDEX
    Explanations

    actions followed by specifics

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

    The neuron is sensitive to quantitative or technical measurements—words and phrases that convey numbers, units, thresholds, or other precise metrics.

    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
     kvě
    -1.55
     户型
    -1.49
    stånd
    -1.47
     distr
    -1.41
     perman
    -1.41
     Encyclopaedia
    -1.36
    fél
    -1.36
    ñó
    -1.35
     frecu
    -1.35
     promin
    -1.34
    POSITIVE LOGITS
     about
    1.65
     this
    1.54
     can
    1.52
     into
    1.45
    。
    1.44
     of
    1.40
     have
    1.39
     Technology
    1.37
       
    1.36
    0
    1.35
    Activations Density 0.130%

    No Known Activations