© 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. 130555
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Variante
    -0.06
     మరి
    -0.06
     ஒன்று
    -0.06
     ngay
    -0.06
     पावर
    -0.06
    myst
    -0.06
     complicate
    -0.05
    詃
    -0.05
    Ridge
    -0.05
    有一种
    -0.05
    POSITIVE LOGITS
    ไ
    0.06
     التي
    0.06
    確かに
    0.06
    ையாள
    0.06
    வற்றை
    0.06
    も
    0.06
     ומ
    0.06
    เยี่ยม
    0.06
     '-':
    0.06
    以及
    0.06
    Activations Density 0.000%

    No Known Activations