© 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. 117900
    Prev
    Next
    INDEX
    Explanations

    license copyright rights terms

    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
     easily
    -0.07
    там
    -0.06
     şeyi
    -0.06
     легко
    -0.06
     там
    -0.06
     easy
    -0.06
     взял
    -0.06
     iets
    -0.06
    周辺
    -0.06
     aici
    -0.06
    POSITIVE LOGITS
     Америка
    0.07
     الجزء
    0.06
    کرین
    0.06
    កំណត់
    0.06
    ………
    0.06
     लास्ट
    0.06
     famosa
    0.06
     Amerika
    0.06
    䊀
    0.06
     últimas
    0.06
    Activations Density 0.008%

    No Known Activations