© 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. 70308
    Prev
    Next
    INDEX
    Explanations

    HTTP server requests

    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
      
    -2.28
     ahşap
    -2.23
     -
    -2.23
     Inſ
    -2.23
     posteriormente
    -2.17
    心中的
    -2.14
     rompe
    -2.14
     ücretsiz
    -2.11
    亖
    -2.09
     perſon
    -2.08
    POSITIVE LOGITS
    .,
    2.61
     公园
    2.50
    ></
    2.31
    g
    2.27
     измене
    2.20
    几乎
    2.19
    y
    2.17
    )]$
    2.16
    ))$.
    2.13
    哧
    2.13
    Activations Density 0.041%

    No Known Activations