© 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. 68405
    Prev
    Next
    INDEX
    Explanations

    color and code syntax

    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
     from
    -2.23
     it
    -1.81
     about
    -1.80
    為に
    -1.73
     like
    -1.72
     in
    -1.67
     That
    -1.59
     on
    -1.58
    jaguar
    -1.55
     that
    -1.50
    POSITIVE LOGITS
     faciliter
    1.78
     作り方
    1.67
    そして
    1.66
    UCIÓN
    1.58
    höhung
    1.57
     dekoratif
    1.54
    Their
    1.53
     absolut
    1.52
    けどね
    1.49
    Кроме
    1.47
    Activations Density 0.000%

    No Known Activations