© 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. 93108
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
     américains
    -1.09
     savag
    -1.09
     unele
    -1.07
     quizá
    -1.05
     entren
    -1.02
     quizás
    -1.02
     мужская
    -1.02
     местных
    -1.00
    一堆
    -0.99
    arreglo
    -0.99
    POSITIVE LOGITS
     république
    1.11
    garder
    1.10
    onnaise
    1.08
    левой
    1.08
     ремон
    1.07
     relacion
    1.06
     hebat
    1.05
    WebServlet
    1.04
    四月
    1.03
     retten
    1.02
    Activations Density 0.010%

    No Known Activations