© 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. 66704
    Prev
    Next
    INDEX
    Explanations

    UI elements and locations

    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
     coroa
    -1.24
     groote
    -1.17
     gebre
    -1.15
     moldura
    -1.09
     sudadera
    -1.08
     coronel
    -1.05
     getroffen
    -1.04
     entière
    -1.04
     kategor
    -1.03
    technologies
    -1.03
    POSITIVE LOGITS
     of
    1.67
     вони
    1.07
     {
    1.06
    홈
    1.02
     to
    0.97
    你的
    0.97
    就可以了
    0.96
     где
    0.96
     leurs
    0.94
     where
    0.93
    Activations Density 0.084%

    No Known Activations