© 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. 117294
    Prev
    Next
    INDEX
    Explanations

    index, 2, 3, 6, 8

    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
     totalled
    -0.06
     Zus
    -0.06
     artich
    -0.05
     ancestor
    -0.05
     cả
    -0.05
    utuskan
    -0.05
     poodle
    -0.05
     Museums
    -0.05
     は
    -0.05
    <footer>
    -0.05
    POSITIVE LOGITS
    سبة
    0.06
     някои
    0.06
     dimensi
    0.06
    বৃত্ত
    0.06
     ಅವಕಾಶ
    0.06
     porém
    0.06
     ಪ್ರತಿ
    0.06
     egli
    0.06
     gennem
    0.06
    なく
    0.06
    Activations Density 0.015%

    No Known Activations