© 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. 34-GEMMASCOPE-RES-131K
    7. 37880
    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
    anjang
    -0.85
    落实
    -0.84
     vaca
    -0.84
     astron
    -0.83
    送料
    -0.82
    gangenen
    -0.81
    旁邊
    -0.81
     lobos
    -0.81
     hect
    -0.79
     albu
    -0.79
    POSITIVE LOGITS
     ранее
    0.90
    vocato
    0.85
    Preparazione
    0.84
    phim
    0.84
    ]<
    0.84
    ]=='
    0.82
    mored
    0.81
    jourd
    0.81
    '){
    0.79
     lact
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.