© 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. 71303
    Prev
    Next
    INDEX
    Explanations

    code and non--English words

    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
    肩膀
    -1.06
     Sekret
    -1.05
    みに
    -1.03
    っこう
    -1.02
    佧
    -1.02
    mero
    -1.02
     Komple
    -1.01
     dashboard
    -0.99
     Kompet
    -0.98
     البته
    -0.98
    POSITIVE LOGITS
     unieke
    1.09
     combinatie
    1.06
     femenino
    1.01
     indruk
    0.97
     sucedido
    0.95
     ومل
    0.94
     ^{\
    0.94
     donker
    0.94
    новая
    0.92
    ולוג
    0.92
    Activations Density 0.005%

    No Known Activations