© 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. 36176
    Prev
    Next
    INDEX
    Explanations

    physical dimension: diameter

    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
     cũng
    -2.69
     które
    -2.55
    irical
    -2.52
     surprising
    -2.50
     aptly
    -2.45
     現在
    -2.45
     There
    -2.42
     unexpectedly
    -2.42
    ibrill
    -2.39
    .},
    -2.34
    POSITIVE LOGITS
     disiplin
    2.67
    .
    2.50
     opsi
    2.36
     olu
    2.34
     etik
    2.31
    🌳
    2.31
     onze
    2.30
    有个
    2.27
     bizi
    2.25
     kafe
    2.23
    Activations Density 0.025%

    No Known Activations