© 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. 73860
    Prev
    Next
    INDEX
    Explanations

    structured data and code

    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
     whofe
    -1.16
     italianos
    -1.13
     cidades
    -1.09
     voks
    -1.09
    masque
    -1.09
    karna
    -1.08
     japoneses
    -1.07
     eléctricas
    -1.06
    kese
    -1.06
     või
    -1.05
    POSITIVE LOGITS
    :
    1.27
    民众
    1.08
    l
    1.07
    al
    1.05
    MASK
    1.04
    R
    1.04
     one
    1.03
    el
    1.03
    C
    1.02
    J
    1.02
    Activations Density 0.001%

    No Known Activations