© 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. 39478
    Prev
    Next
    INDEX
    Explanations

    simple things

    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
     klinik
    -1.06
    futter
    -1.04
     saksi
    -1.02
     kabát
    -1.01
     minta
    -1.01
    käse
    -1.01
    картинка
    -1.00
    Minh
    -0.94
    реги
    -0.94
     rése
    -0.93
    POSITIVE LOGITS
     now
    1.10
    ertes
    0.97
     alcuna
    0.96
     Tell
    0.95
    時間が
    0.95
    roke
    0.91
     then
    0.90
    --)
    
    0.89
    而
    0.88
     ಗ
    0.88
    Activations Density 0.017%

    No Known Activations