© 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. 129825
    Prev
    Next
    INDEX
    Explanations

    tokens after specific punctuation

    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
    స్క
    -0.07
     प्रारंभिक
    -0.07
     ndị
    -0.06
    が存在
    -0.06
     मंदिरों
    -0.06
     ayaa
    -0.06
     एवं
    -0.06
     tempered
    -0.06
    があった
    -0.06
    我们也
    -0.06
    POSITIVE LOGITS
     fue
    0.07
    जैसा
    0.07
     ഭക്ഷണം
    0.06
    Even
    0.06
    como
    0.06
    BP
    0.06
     হলেন
    0.06
    像
    0.05
    בין
    0.05
     skoro
    0.05
    Activations Density 0.001%

    No Known Activations