© 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. 119168
    Prev
    Next
    INDEX
    Explanations

    code block terminators

    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
     povinn
    -0.06
    ここで
    -0.05
    为了
    -0.05
     enquanto
    -0.05
     ausschließlich
    -0.05
     недалеко
    -0.05
     súčas
    -0.05
    kona
    -0.05
    を有する
    -0.05
    同时
    -0.05
    POSITIVE LOGITS
     Hydra
    0.07
     nonchal
    0.07
    というのは
    0.06
     pesky
    0.06
     dazzling
    0.06
     northeastern
    0.06
     adequately
    0.06
     getting
    0.06
     aberration
    0.06
    фект
    0.06
    Activations Density 0.010%

    No Known Activations