© 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. 116571
    Prev
    Next
    INDEX
    Explanations

    triple digits

    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
     чаще
    -0.07
     commonly
    -0.06
    很少
    -0.06
     可以
    -0.06
     sometimes
    -0.06
    ется
    -0.06
     нередко
    -0.06
    しばらく
    -0.06
    shuffle
    -0.06
     rarely
    -0.06
    POSITIVE LOGITS
     ήταν
    0.06
     সংশ্লিষ্ট
    0.06
     ಬಗ್ಗೆ
    0.06
     był
    0.06
    📣
    0.05
    周边
    0.05
     salaried
    0.05
    ------
    0.05
    ("--------
    0.05
    professional
    0.05
    Activations Density 0.004%

    No Known Activations