© 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. 106449
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Entreprises
    -0.78
     テレビ
    -0.77
     hand
    -0.77
     ebenso
    -0.77
     flesh
    -0.77
    setVisibility
    -0.77
     Ceinture
    -0.75
     intensive
    -0.74
     Pits
    -0.73
     Hej
    -0.73
    POSITIVE LOGITS
    LSU
    0.98
    Pdf
    0.91
     LSU
    0.90
    Crítica
    0.84
     Algerian
    0.84
     Baton
    0.81
    itext
    0.81
     Shreveport
    0.78
    پزخانه
    0.78
     Чита
    0.78
    Activations Density 0.004%

    No Known Activations