© 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. 10-GEMMASCOPE-RES-131K
    7. 9162
    Prev
    Next
    INDEX
    Explanations

    Netflix shows and series

    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
    ㎝
    -1.23
     αλλά
    -1.16
    ว์
    -1.14
    ∊
    -1.14
    operand
    -1.13
    Hawai
    -1.13
    呜
    -1.13
    ဤ
    -1.12
    Ց
    -1.12
     citi
    -1.10
    POSITIVE LOGITS
     to
    1.30
    𝟰
    1.27
     Netflix
    1.20
     realmente
    1.18
    thentic
    1.17
     explain
    1.13
     '',
    1.12
    矬
    1.12
     will
    1.11
     为什么
    1.11
    Activations Density 0.037%

    No Known Activations