© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118107
    Prev
    Next
    INDEX
    Explanations

    programming annotations and decorators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Всё
    -0.07
     বাক্স
    -0.06
     אני
    -0.06
     eventualmente
    -0.06
     そして
    -0.06
    Requested
    -0.06
    hibition
    -0.06
     الصفحه
    -0.05
     benthic
    -0.05
    SINGLE
    -0.05
    POSITIVE LOGITS
     such
    0.08
     verschiedene
    0.06
     redan
    0.06
     такая
    0.06
     make
    0.06
     typical
    0.06
     already
    0.06
     sådan
    0.06
     indicadores
    0.06
     такую
    0.06
    Activations Density 0.002%

    No Known Activations