© 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. 30042
    Prev
    Next
    INDEX
    Explanations

    addresses and postal codes

    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
     even
    -1.25
     its
    -1.13
     recently
    -1.09
     any
    -1.07
    lsea
    -1.04
     like
    -1.04
     already
    -1.02
     this
    -0.98
    逮捕
    -0.98
     Even
    -0.96
    POSITIVE LOGITS
    tehen
    1.06
    Unnamed
    0.99
    Musique
    0.96
     incredi
    0.94
     increíble
    0.94
     excellente
    0.93
     énorm
    0.93
    Zdrav
    0.93
     impecable
    0.92
     ‎
    0.92
    Activations Density 0.009%

    No Known Activations