© 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. 22-GEMMASCOPE-RES-131K
    7. 64589
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     וכן
    -1.77
     that
    -1.71
    Кроме
    -1.61
    کفش
    -1.52
     oraz
    -1.45
    angkap
    -1.42
     wykor
    -1.41
    以上です
    -1.41
     ビキニ
    -1.40
    ではまた
    -1.38
    POSITIVE LOGITS
    {
    1.75
     {
    1.73
    ve
    1.61
    </i>
    1.56
    no
    1.55
     ~
    1.55
    ro
    1.54
    a
    1.52
    ce
    1.49
    .’
    1.48
    Activations Density 0.000%

    No Known Activations