© 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. 10074
    Prev
    Next
    INDEX
    Explanations

    if

    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
     unable
    -1.68
     easily
    -1.54
     enough
    -1.52
     without
    -1.48
     more
    -1.47
    äls
    -1.46
     září
    -1.41
     conversar
    -1.40
     easier
    -1.39
    /*++
    -1.38
    POSITIVE LOGITS
     quelles
    1.43
     diego
    1.41
     redondo
    1.41
     variétés
    1.34
     rigue
    1.31
     prado
    1.28
     verres
    1.26
     trente
    1.24
     accompagner
    1.24
     antonio
    1.23
    Activations Density 0.175%

    No Known Activations