© 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. 64374
    Prev
    Next
    INDEX
    Explanations

    preposition phrases for context

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

    The neuron detects numerical measurements and their associated units in the text.

    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
    ✭✭
    -1.16
    :✨
    -1.09
    idenav
    -1.07
    Биография
    -1.06
    intahan
    -0.98
    
    -0.98
    手順
    -0.97
    dreamstime
    -0.96
     extraordin
    -0.95
     grids
    -0.95
    POSITIVE LOGITS
     χρήση
    1.18
     both
    0.98
    chte
    0.97
     déclarations
    0.96
     saudável
    0.96
    sime
    0.93
     pensent
    0.93
    don
    0.89
    Luckily
    0.89
     chegar
    0.88
    Activations Density 0.058%

    No Known Activations