© 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. 129733
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by common words

    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
     надеюсь
    -0.06
     ಸುಮ
    -0.06
     عنده
    -0.06
     senyawa
    -0.06
     femenino
    -0.06
    ว่า
    -0.06
     sebagai
    -0.06
     femenina
    -0.06
     લગભગ
    -0.05
     kanye
    -0.05
    POSITIVE LOGITS
     обычно
    0.06
     usually
    0.06
     Обычно
    0.06
     通常
    0.06
    Came
    0.06
    సం
    0.06
     typically
    0.06
     često
    0.06
    র্কের
    0.06
    ামের
    0.06
    Activations Density 0.018%

    No Known Activations