© 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. 104396
    Prev
    Next
    INDEX
    Explanations

    "in this case"

    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
     this
    -1.61
     these
    -1.50
     today
    -1.29
     এই
    -1.28
     then
    -1.23
     tämän
    -1.18
     nowadays
    -1.13
     tässä
    -1.13
    此时
    -1.05
     thereupon
    -1.05
    POSITIVE LOGITS
    sedes
    0.90
     chodzi
    0.88
     a
    0.88
    綿
    0.87
     plutôt
    0.87
     været
    0.87
     pierna
    0.87
     глазами
    0.86
     wieder
    0.86
     Sinne
    0.84
    Activations Density 0.054%

    No Known Activations