© 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. 70717
    Prev
    Next
    INDEX
    Explanations

    do followed by pronouns or articles

    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
     disminu
    -1.98
     señala
    -1.89
    赑
    -1.81
    osoever
    -1.77
     aparentemente
    -1.77
     moviliz
    -1.74
     añadió
    -1.73
     verdaderamente
    -1.72
     dezelve
    -1.71
     detalló
    -1.70
    POSITIVE LOGITS
    но
    1.84
    </em>
    1.64
    ">
    1.63
     It
    1.61
    ie
    1.54
    ному
    1.54
     Affaires
    1.52
     ,
    1.51
     شده
    1.49
    te
    1.48
    Activations Density 0.350%

    No Known Activations