© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128695
    Prev
    Next
    INDEX
    Explanations

    posted 1d ago

    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
    これまで
    -0.07
     desar
    -0.06
     use
    -0.06
     discontinuities
    -0.06
    कारा
    -0.06
     uso
    -0.06
     Теперь
    -0.06
     appreciable
    -0.06
     câte
    -0.06
     extent
    -0.06
    POSITIVE LOGITS
    的一個
    0.06
     paycheck
    0.06
     обучения
    0.06
     увеличения
    0.06
    nation
    0.06
    的一个
    0.06
     ৭৮
    0.06
     sarebbe
    0.06
    election
    0.06
     ১৮
    0.06
    Activations Density 0.003%

    No Known Activations