© 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. 120564
    Prev
    Next
    INDEX
    Explanations

    new words in multiple languages

    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
     Thus
    -0.07
     எதி
    -0.07
     Therefore
    -0.06
     THERE
    -0.06
     plast
    -0.06
     kèm
    -0.06
    znej
    -0.06
     Dadurch
    -0.05
    `}
    -0.05
     dvije
    -0.05
    POSITIVE LOGITS
     знаю
    0.07
    phthalm
    0.07
     partage
    0.07
     отказыва
    0.06
     sabía
    0.06
     वर्गी
    0.06
     спраши
    0.06
     selber
    0.06
     salah
    0.06
     настолько
    0.06
    Activations Density 0.001%

    No Known Activations