© 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. 45723
    Prev
    Next
    INDEX
    Explanations

    providing you with

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

    The neuron is strongly triggered by the preposition “with.”

    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
     it
    -1.94
     this
    -1.84
    2
    -1.82
    지만
    -1.56
    1
    -1.55
     już
    -1.54
     kwamba
    -1.52
    or
    -1.50
     each
    -1.42
     whet
    -1.41
    POSITIVE LOGITS
     a
    3.03
    
    1.95
    諼
    1.91
    躂
    1.89
    ICION
    1.81
     calabaza
    1.80
     something
    1.79
    臵
    1.76
     scrivere
    1.71
     policías
    1.69
    Activations Density 0.019%

    No Known Activations