© 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. 130239
    Prev
    Next
    INDEX
    Explanations

    code comments and programming constructs

    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
     γιατί
    -0.07
    この
    -0.07
    این
    -0.07
     cellulose
    -0.07
     porque
    -0.07
    πά
    -0.07
    皆さん
    -0.06
    男性
    -0.06
     ainult
    -0.06
    因为
    -0.06
    POSITIVE LOGITS
     using
    0.06
     Travel
    0.06
     travel
    0.06
    瞬间
    0.06
     html
    0.06
     실험
    0.06
     мг
    0.06
     हेतु
    0.06
     ዘዴ
    0.06
    临时
    0.06
    Activations Density 0.003%

    No Known Activations