© 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. 22-GEMMASCOPE-RES-131K
    7. 95730
    Prev
    Next
    INDEX
    Explanations

    bracketed expressions on lists

    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
     bayan
    -1.09
    ANIEL
    -1.09
     fotografi
    -1.03
     patate
    -1.01
     taba
    -1.00
     balon
    -0.99
    İyi
    -0.98
     systé
    -0.97
    Çok
    -0.97
     {,
    -0.97
    POSITIVE LOGITS
     In
    0.94
     both
    0.90
     Both
    0.89
    ໄ
    0.86
    дає
    0.86
     zowel
    0.84
     Here
    0.82
    人家
    0.80
    e
    0.78
     Along
    0.77
    Activations Density 0.001%

    No Known Activations