© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72509
    Prev
    Next
    INDEX
    Explanations

    legal, international, and grammatical markers

    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
    ︕
    -1.68
     הם
    -1.67
     trovano
    -1.55
    お弁当
    -1.55
     Mereka
    -1.55
    曏
    -1.54
     didik
    -1.52
    こういった
    -1.50
    もうすぐ
    -1.47
    コチラ
    -1.41
    POSITIVE LOGITS
     of
    1.79
    \
    1.56
    tinta
    1.56
    tallet
    1.55
     entonces
    1.53
     Other
    1.52
    ingat
    1.49
    copie
    1.48
    kopi
    1.48
     jetzt
    1.47
    Activations Density 0.003%

    No Known Activations