© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104366
    Prev
    Next
    INDEX
    Explanations

    numbers and proportions

    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
     також
    -1.27
     tambi
    -1.25
     Füße
    -1.21
    
    -1.21
     ventajas
    -1.16
     добавил
    -1.14
    helped
    -1.12
    ナイキ
    -1.09
     również
    -1.09
     experto
    -1.09
    POSITIVE LOGITS
     which
    2.33
     and
    1.49
     of
    1.45
     so
    1.08
    lotten
    1.05
     menyenangkan
    1.04
    “)
    1.03
     isang
    1.02
     for
    1.00
    pecially
    1.00
    Activations Density 0.047%

    No Known Activations