© 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. 75443
    Prev
    Next
    INDEX
    Explanations

    describes things that is or that is

    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
     даже
    -1.46
    żer
    -1.41
     навіть
    -1.35
     menik
    -1.30
     terke
    -1.29
     حتی
    -1.27
     hilos
    -1.26
     använda
    -1.25
    šo
    -1.23
     akrab
    -1.23
    POSITIVE LOGITS
     part
    1.48
     to
    1.41
     most
    1.40
     generally
    1.36
     always
    1.36
     esperamos
    1.34
     sometimes
    1.33
     the
    1.29
     not
    1.28
     usually
    1.24
    Activations Density 0.059%

    No Known Activations