© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71937
    Prev
    Next
    INDEX
    Explanations

    both and other languages

    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
     when
    -1.88
     other
    -1.49
     because
    -1.38
     if
    -1.37
     during
    -1.22
     after
    -1.18
     that
    -1.17
     or
    -1.13
     in
    -1.13
     at
    -1.12
    POSITIVE LOGITS
    ทั้ง
    1.91
     både
    1.86
     everything
    1.54
     both
    1.45
     zowel
    1.37
     nejen
    1.34
     сначала
    1.30
    both
    1.30
    BOTH
    1.28
     weder
    1.26
    Activations Density 0.247%

    No Known Activations