© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120230
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
     that
    -0.07
     PHOTOS
    -0.06
     γνωσ
    -0.06
     pines
    -0.06
     аналоги
    -0.06
    photos
    -0.06
     lawyers
    -0.06
     lawyer
    -0.06
    已知
    -0.06
     photos
    -0.06
    POSITIVE LOGITS
     percussion
    0.08
     Beyoncé
    0.07
     urinal
    0.07
     சுற்றுச்சூழ
    0.07
     তাঁর
    0.06
     Destruction
    0.06
    蹴
    0.06
     prevenir
    0.06
     Shell
    0.06
    冲击
    0.06
    Activations Density 0.008%

    No Known Activations