© 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. 69098
    Prev
    Next
    INDEX
    Explanations

    computing devices and storage

    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
     actually
    -1.22
     just
    -1.21
     to
    -1.20
      
    -1.17
     all
    -1.13
     again
    -1.12
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.11
     Ainsi
    -1.09
     simply
    -1.09
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.08
    POSITIVE LOGITS
    ⽆
    1.41
     filós
    1.39
    lleg
    1.36
     informé
    1.32
    μισ
    1.27
    inių
    1.27
     imponer
    1.26
    ṇ
    1.25
    från
    1.25
     ibang
    1.25
    Activations Density 0.464%

    No Known Activations