© 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. 22-GEMMASCOPE-RES-131K
    7. 72724
    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
     teater
    -1.48
     honlap
    -1.46
    şan
    -1.45
     sekunder
    -1.43
     stort
    -1.42
     butik
    -1.39
     beker
    -1.38
    身旁
    -1.36
     lilla
    -1.35
     keren
    -1.34
    POSITIVE LOGITS
    ;
    1.53
     seguintes
    1.52
     protože
    1.44
    如图
    1.40
    It
    1.36
    But
    1.35
     дисци
    1.30
     aanzien
    1.30
    んですよ
    1.30
    ちな
    1.29
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.