© 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. 58014
    Prev
    Next
    INDEX
    Explanations

    upright and erect posture

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

    This neuron activates specifically on the occurrence of the word “upright.”

    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
    ING
    -2.88
    in
    -2.67
    ↵
    -2.39
     üb
    -2.38
    {
    -2.31
        
    -2.20
     Lösungs
    -2.20
    м
    -2.16
     to
    -2.16
          
    -2.14
    POSITIVE LOGITS
     ſta
    3.16
    
    2.75
     ſte
    2.61
    　　——
    2.52
    नलोड
    2.52
    鷓
    2.48
    ｂ
    2.45
    是非常
    2.41
    ～～
    2.39
     纹身
    2.39
    Activations Density 0.001%

    No Known Activations