© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117663
    Prev
    Next
    INDEX
    Explanations

    code comments and programming keywords

    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
     certain
    -0.06
     Certain
    -0.06
     high
    -0.06
     all
    -0.06
     no
    -0.06
    total
    -0.06
     The
    -0.06
     one
    -0.06
     their
    -0.06
     any
    -0.05
    POSITIVE LOGITS
     защото
    0.07
    していますが
    0.07
    しますが
    0.07
     toujours
    0.07
    因為
    0.06
     ඔහු
    0.06
     podob
    0.06
     전에
    0.06
    同様
    0.06
     үчүн
    0.06
    Activations Density 0.002%

    No Known Activations