© 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. 70599
    Prev
    Next
    INDEX
    Explanations

    CSS selectors

    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
    oia
    -1.42
    
    -1.38
    asca
    -1.38
     pomocou
    -1.34
     bénéficiaire
    -1.34
     geschenk
    -1.34
     Kartu
    -1.33
    になるので
    -1.33
    쨩
    -1.32
     PopupWindow
    -1.31
    POSITIVE LOGITS
     quickly
    1.41
    ar
    1.38
    N
    1.37
     clearly
    1.36
     offers
    1.35
     only
    1.34
     also
    1.33
     information
    1.32
     set
    1.31
    v
    1.27
    Activations Density 0.004%

    No Known Activations