© 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. 9151
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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
    跸
    -1.62
     فقط
    -1.43
    Hmmm
    -1.40
    ligt
    -1.38
    ктей
    -1.36
    嗵
    -1.31
    delige
    -1.30
    Believe
    -1.30
    umenter
    -1.29
    olge
    -1.27
    POSITIVE LOGITS
     of
    2.02
     such
    1.87
     like
    1.83
     many
    1.83
     but
    1.78
     new
    1.63
     other
    1.53
     two
    1.50
     have
    1.48
     used
    1.47
    Activations Density 0.176%

    No Known Activations