© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106634
    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
     laim
    -1.80
     pakan
    -1.62
     atve
    -1.57
     meil
    -1.55
     veik
    -1.38
     teka
    -1.36
     krep
    -1.35
     darbo
    -1.35
     toki
    -1.34
     sako
    -1.34
    POSITIVE LOGITS
     najbol
    1.27
     pokra
    1.26
     ljudi
    1.25
     žele
    1.25
     žena
    1.22
    Недоліки
    1.21
     jezik
    1.20
     potreb
    1.19
    FTIR
    1.18
     žel
    1.16
    Activations Density 0.005%

    No Known Activations