© 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. 40251
    Prev
    Next
    INDEX
    Explanations

    programming and data fields

    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
    と
    -1.45
    を
    -1.39
     is
    -1.36
    や
    -1.33
    で
    -1.24
    そして
    -1.20
    が
    -1.19
    などを
    -1.18
    では
    -1.16
     を
    -1.15
    POSITIVE LOGITS
    化する
    1.38
     tager
    1.21
    の準備
    1.20
     betyder
    1.20
     brukt
    1.19
     slår
    1.19
     novos
    1.16
    нять
    1.14
     DÍA
    1.13
    感じで
    1.13
    Activations Density 0.042%

    No Known Activations