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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131062
    Prev
    Next
    INDEX
    Explanations

    numbers and locations

    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
     what
    -0.08
     что
    -0.07
    去做
    -0.07
     hacer
    -0.07
    去看
    -0.07
     чем
    -0.06
    这
    -0.06
     quello
    -0.06
    那
    -0.06
    ものが
    -0.06
    POSITIVE LOGITS
     eight
    0.08
     seven
    0.07
    various
    0.07
     Morning
    0.07
     five
    0.06
    Thursday
    0.06
    five
    0.06
     различных
    0.06
    amak
    0.06
    four
    0.06
    Activations Density 0.001%

    No Known Activations