© 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. 118238
    Prev
    Next
    INDEX
    Explanations

    Makeover

    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
    包括
    -0.07
     πριν
    -0.06
    PLEASE
    -0.06
     दोन्ही
    -0.06
     قبل
    -0.06
    Trước
    -0.06
     trước
    -0.06
     koje
    -0.06
     بدون
    -0.06
    Before
    -0.06
    POSITIVE LOGITS
    搭配
    0.06
    unpublished
    0.06
    雪
    0.06
     finished
    0.06
     lunes
    0.06
     inimes
    0.06
    PACT
    0.06
     {},
    0.06
    意外
    0.05
     Lorenz
    0.05
    Activations Density 0.001%

    No Known Activations