© 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. 19315
    Prev
    Next
    INDEX
    Explanations

    replaced by

    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
     \
    -1.37
    戢
    -1.31
     ciascuno
    -1.28
     formulaire
    -1.27
     součas
    -1.27
     една
    -1.26
    alucía
    -1.26
     there
    -1.25
     سبورت
    -1.25
    tidas
    -1.23
    POSITIVE LOGITS
     вместо
    1.49
    Replacing
    1.47
     Replacing
    1.45
    Instead
    1.36
     केवल
    1.35
     invece
    1.34
     Instead
    1.34
     Substituting
    1.32
    </h4>
    1.30
     replacing
    1.30
    Activations Density 0.054%

    No Known Activations