© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123980
    Prev
    Next
    INDEX
    Explanations

    one followed by noun

    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_10/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
    ⓸
    -1.45
    𝗌
    -1.38
     våre
    -1.34
    1
    -1.33
     trovare
    -1.27
    rowy
    -1.25
    sync
    -1.24
     of
    -1.24
     seines
    -1.23
     zeven
    -1.23
    POSITIVE LOGITS
     there
    1.70
     that
    1.54
     aquellos
    1.42
     碎
    1.38
     婚礼
    1.32
    jenigen
    1.30
    }{
    1.29
    I
    1.29
     宣传
    1.29
     cocción
    1.27
    Activations Density 0.077%

    No Known Activations