© 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. 13053
    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
    づけ
    -1.41
     montaje
    -1.34
    向けの
    -1.34
    さぁ
    -1.32
     cerâmica
    -1.31
    こともあり
    -1.30
    ところに
    -1.29
    ようになる
    -1.27
    lyon
    -1.26
    んですよね
    -1.23
    POSITIVE LOGITS
    がありますが
    1.78
    があります
    1.62
    などが
    1.48
    <bos>
    1.46
    紡
    1.41
    但却
    1.39
    但这
    1.38
    <0xA3>
    1.37
    だが
    1.36
    内容は
    1.36
    Activations Density 0.000%

    No Known Activations