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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13205
    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
     such
    -1.51
     this
    -1.35
     their
    -1.34
     that
    -1.28
     which
    -1.27
     zobaczyć
    -1.13
     mieli
    -1.13
    März
    -1.08
     brancas
    -1.08
     saisi
    -1.07
    POSITIVE LOGITS
    こちらも
    1.25
     streamlining
    1.25
    ha
    1.23
    これも
    1.20
    p
    1.16
    in
    1.15
     nuevamente
    1.09
    r
    1.09
     alcune
    1.08
     amd
    1.08
    Activations Density 0.000%

    No Known Activations