© 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. 117348
    Prev
    Next
    INDEX
    Explanations

    serialization and imports

    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
    ,
    -0.06
     intrinsically
    -0.06
     dogged
    -0.06
    畄
    -0.06
     وم
    -0.06
     hamstring
    -0.06
     offering
    -0.05
    хів
    -0.05
    ♏
    -0.05
    </td>
    -0.05
    POSITIVE LOGITS
     ένα
    0.08
     ใน
    0.08
    Disable
    0.08
     của
    0.08
     ഒരു
    0.08
     sebuah
    0.07
     एक
    0.07
     একটি
    0.07
     любых
    0.07
    の中に
    0.07
    Activations Density 0.001%

    No Known Activations