© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84222
    Prev
    Next
    INDEX
    Explanations

    countries and territories

    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
     it
    -1.63
    ,\\
    -1.39
    者を
    -1.34
     and
    -1.30
     มัน
    -1.29
    ücher
    -1.26
    ⁧
    -1.24
     сделан
    -1.23
    ilien
    -1.23
    頃に
    -1.23
    POSITIVE LOGITS
     are
    1.75
     of
    1.48
     sebuah
    1.27
     termasuk
    1.25
    所以在
    1.24
     –
    1.17
     when
    1.16
      
    1.14
     ซึ่ง
    1.14
     —
    1.13
    Activations Density 0.218%

    No Known Activations