© 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. 79744
    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
    が
    -1.88
    は
    -1.76
    を
    -1.66
    なので
    -1.66
     are
    -1.57
    ที่
    -1.44
    もちゃ
    -1.42
    などの
    -1.42
    による
    -1.41
    ！"
    -1.40
    POSITIVE LOGITS
     and
    1.98
    感じです
    1.72
    様な
    1.65
    ところに
    1.55
    ことも
    1.52
    ようになります
    1.49
    ことがある
    1.47
    コチラ
    1.41
    ところは
    1.41
    際には
    1.41
    Activations Density 0.000%

    No Known Activations