© 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. 28368
    Prev
    Next
    INDEX
    Explanations

    items following including

    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
     then
    -1.20
     also
    -1.11
     natomiast
    -1.10
    も同じ
    -1.09
     either
    -1.09
     również
    -1.09
     will
    -1.09
     likewise
    -0.99
     invece
    -0.99
    then
    -0.94
    POSITIVE LOGITS
     which
    1.21
     ones
    1.18
    rably
    1.04
    ingl
    1.03
     uur
    0.97
     ￥
    0.95
     recentemente
    0.95
    *?
    0.94
    ሚ
    0.94
    recently
    0.93
    Activations Density 0.079%

    No Known Activations