© 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. 28593
    Prev
    Next
    INDEX
    Explanations

    quantifiers and determiners

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    日に
    -1.14
    日を
    -0.99
    alad
    -0.98
    虽说
    -0.98
    甦
    -0.96
    戏剧
    -0.91
    轍
    -0.90
    を
    -0.89
     épo
    -0.89
    書店
    -0.87
    POSITIVE LOGITS
    を探す
    1.16
    感じです
    1.10
    ってる
    1.08
    で見る
    1.07
    other
    1.05
    場所に
    0.98
    に挑戦
    0.98
     your
    0.97
     leggere
    0.95
     nasze
    0.94
    Activations Density 0.096%

    No Known Activations