© 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. 116294
    Prev
    Next
    INDEX
    Explanations

    programming function calls or declarations

    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
     these
    -0.09
     each
    -0.07
     этих
    -0.07
     каждого
    -0.07
     deze
    -0.06
     těchto
    -0.06
     هذه
    -0.06
     concerning
    -0.06
    each
    -0.06
    这些
    -0.06
    POSITIVE LOGITS
     avulla
    0.06
     väik
    0.06
    Funds
    0.06
    وري
    0.06
     fragilis
    0.06
     moins
    0.06
    ՝
    0.06
    笉
    0.06
     ゼ
    0.06
    することで
    0.06
    Activations Density 0.002%

    No Known Activations