© 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. 34-GEMMASCOPE-RES-131K
    7. 3660
    Prev
    Next
    INDEX
    Explanations

    place of residence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Tir
    -0.77
     Keith
    -0.72
    础
    -0.71
     المك
    -0.70
    去看
    -0.70
    дку
    -0.70
    碌
    -0.69
    珑
    -0.68
     Call
    -0.67
     marinho
    -0.67
    POSITIVE LOGITS
     residence
    4.38
     residency
    3.34
    residence
    3.25
    Residence
    2.98
     Residence
    2.88
     residences
    2.86
     RESIDENCE
    2.63
     residen
    2.61
     reside
    2.52
     resident
    2.50
    Activations Density 0.039%

    No Known Activations