© 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. 56693
    Prev
    Next
    INDEX
    Explanations

    html punctuation and code

    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
     pezzi
    -1.03
     uovo
    -1.01
    НЯ
    -0.98
     cucchiaio
    -0.97
    出来て
    -0.95
     bicchiere
    -0.94
     verständ
    -0.90
     sabbia
    -0.89
     シート
    -0.88
     vecchi
    -0.88
    POSITIVE LOGITS
     ">
    0.98
     ""
    0.97
    ">
    0.94
    ()">
    0.92
     />
    0.90
     et
    0.90
     href
    0.90
     ()
    0.89
     ();
    0.88
    ...,
    0.86
    Activations Density 0.011%

    No Known Activations